filename
string | title
string | abstract
string | pred_lin
sequence | prompt
string |
|---|---|---|---|---|
3A830149120.jsonld | Topic Drop and Null Subjects in German | "This study presents new insights into null subjects, topic drop and the interpretation of topic-dropped elements. Besides providing an empirical data survey, it offers explanations to well-known problems, e.g. syncretisms in the context of null-subject licensing or the marginality of dropping an element which carries oblique case. The book constitutes a valuable source for both empirically and theoretically interested (generative) linguists."-- | [
"['lin']",
"['lit']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Topic Drop and Null Subjects in German
- Document Abstract: "This study presents new insights into null subjects, topic drop and the interpretation of topic-dropped elements. Besides providing an empirical data survey, it offers explanations to well-known problems, e.g. syncretisms in the context of null-subject licensing or the marginality of dropping an element which carries oblique case. The book constitutes a valuable source for both empirically and theoretically interested (generative) linguists."--
- Document LIN Search class: ['lin'], ['lit']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A875721826.jsonld | Coherent structures and rotational effects on the flow over spinners of horizontal axis wind turbines | Wind turbine aerodynamics, rotational effects, coherent structures. - Aerodynamik der Windenergieanlage, Rotationseffekte, kohärente Strukturen | [
"['mas']",
"['phy']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Coherent structures and rotational effects on the flow over spinners of horizontal axis wind turbines
- Document Abstract: Wind turbine aerodynamics, rotational effects, coherent structures. - Aerodynamik der Windenergieanlage, Rotationseffekte, kohärente Strukturen
- Document LIN Search class: ['mas'], ['phy']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A866694293.jsonld | Aufkommens- und Entscheidungseffekte von Ertragsteuern | Gemeindeeinkommensteuer, Kernstadt-Umland-Wirkung, Mikrosimulation, Steuerstatistik, Zinsabzugsbeschränkungen, Rechtsformneutralität, Rechtsformentscheidungen, Haftungsbeschränkung, Steuerplanung, Steueraggressivität , Steuerprüfung, Corporate Governance. - Local income taxes, regional tax effects, microsimulation, tax statistics, thin capitalization, organizational form neutrality, choice of legal form, liability limitation, tax avoidance, tax aggressiveness, tax audit | [
"['oek']",
"['jur']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Aufkommens- und Entscheidungseffekte von Ertragsteuern
- Document Abstract: Gemeindeeinkommensteuer, Kernstadt-Umland-Wirkung, Mikrosimulation, Steuerstatistik, Zinsabzugsbeschränkungen, Rechtsformneutralität, Rechtsformentscheidungen, Haftungsbeschränkung, Steuerplanung, Steueraggressivität , Steuerprüfung, Corporate Governance. - Local income taxes, regional tax effects, microsimulation, tax statistics, thin capitalization, organizational form neutrality, choice of legal form, liability limitation, tax avoidance, tax aggressiveness, tax audit
- Document LIN Search class: ['oek'], ['jur']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1830283626.jsonld | Investigation of the effects of raw material density and molecular weight of phenolic resin binders on the properties of lightweight panels based on Paulownia wood | Abstract This thesis focuses on different production process conditions of strand boards (SBs), especially with wood species (Paulownia tomentosa) by various adhesive binders (pMDI) and their influence on the properties of strand boards. The kiri tree is an extremely fast-growing, ring-porous tree with a low density of about 280 kg m-3 and it is mainly grown in plantations. Based on that, this study focused on the production of lightweight strand boards under 500 kg m-3. In the first part of the study, lightweight strand boards were produced at a target density of 300 kg m-3 and 400 kg m-3 ... Zusammenfassung Diese Dissertation befasst sich mit unterschiedlichen Produktionsprozessbedingungen von Spanplatten (SBs), insbesondere mit der neuen Holzart Kiri (Paulownia tomentosa) mit verschiedenen Klebstoffen und deren Einfluss auf die Eigenschaften von Spanplatten. Der Kiri-Baum ist ein extrem schnell wachsender, ringporiger Baum mit einer geringen Dichte von ca. 350 kg m-3 und wird hauptsächlich in Plantagen angebaut. Ausgehend davon konzentrierte sich diese Studie auf die Herstellung von leichten Spanplatten unter 500 kg m-3. Im ersten Teil der Studie wurden leichte Spanplatten mit... | [
"['hor']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Investigation of the effects of raw material density and molecular weight of phenolic resin binders on the properties of lightweight panels based on Paulownia wood
- Document Abstract: Abstract This thesis focuses on different production process conditions of strand boards (SBs), especially with wood species (Paulownia tomentosa) by various adhesive binders (pMDI) and their influence on the properties of strand boards. The kiri tree is an extremely fast-growing, ring-porous tree with a low density of about 280 kg m-3 and it is mainly grown in plantations. Based on that, this study focused on the production of lightweight strand boards under 500 kg m-3. In the first part of the study, lightweight strand boards were produced at a target density of 300 kg m-3 and 400 kg m-3 ... Zusammenfassung Diese Dissertation befasst sich mit unterschiedlichen Produktionsprozessbedingungen von Spanplatten (SBs), insbesondere mit der neuen Holzart Kiri (Paulownia tomentosa) mit verschiedenen Klebstoffen und deren Einfluss auf die Eigenschaften von Spanplatten. Der Kiri-Baum ist ein extrem schnell wachsender, ringporiger Baum mit einer geringen Dichte von ca. 350 kg m-3 und wird hauptsächlich in Plantagen angebaut. Ausgehend davon konzentrierte sich diese Studie auf die Herstellung von leichten Spanplatten unter 500 kg m-3. Im ersten Teil der Studie wurden leichte Spanplatten mit...
- Document LIN Search class: ['hor']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1685888011.jsonld | Frame by frame : a materialist aesthetics of animated cartoons | At publication date, a free ebook version of this title will be available through Luminos, University of California Press's Open Access publishing program. Visit www.luminosoa.org to learn more. In this beautifully written and deeply researched study, Hannah Frank provides an original way to understand American animated cartoons from the Golden Age of animation (1920-1960). In the pre-digital age of the twentieth century, the making of cartoons was mechanized and standardized: thousands of drawings were inked and painted onto individual transparent celluloid sheets (called "cels") and then photographed in succession, a labor-intensive process that was divided across scores of artists and technicians. In order to see the art, labor, and technology of cel animation, Frank slows cartoons down to look frame by frame, finding hitherto unseen aspects of the animated image. What emerges is both a methodology and a highly original account of an art formed on the assembly line Frontmatter -- Contents -- List of Illustrations -- Foreword : Hannah Frank's Pause / Gunning, Tom -- Editor's Introduction / Morgan, Daniel -- Acknowledgments -- Introduction: Looking at Labor -- 1. Animation and Montage; or, Photographic Records of Documents -- 2. A View of the World: Toward a Photographic Theory of Cel Animation -- 3. Pars Pro Toto: Character Animation and the Work of the Anonymous Artist -- 4. The Multiplication of Traces: Xerographic Reproduction and One Hundred and One Dalmatians -- Conclusion: The Labor of Looking -- Notes -- Bibliography -- Index | [
"['rest']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Frame by frame : a materialist aesthetics of animated cartoons
- Document Abstract: At publication date, a free ebook version of this title will be available through Luminos, University of California Press's Open Access publishing program. Visit www.luminosoa.org to learn more. In this beautifully written and deeply researched study, Hannah Frank provides an original way to understand American animated cartoons from the Golden Age of animation (1920-1960). In the pre-digital age of the twentieth century, the making of cartoons was mechanized and standardized: thousands of drawings were inked and painted onto individual transparent celluloid sheets (called "cels") and then photographed in succession, a labor-intensive process that was divided across scores of artists and technicians. In order to see the art, labor, and technology of cel animation, Frank slows cartoons down to look frame by frame, finding hitherto unseen aspects of the animated image. What emerges is both a methodology and a highly original account of an art formed on the assembly line Frontmatter -- Contents -- List of Illustrations -- Foreword : Hannah Frank's Pause / Gunning, Tom -- Editor's Introduction / Morgan, Daniel -- Acknowledgments -- Introduction: Looking at Labor -- 1. Animation and Montage; or, Photographic Records of Documents -- 2. A View of the World: Toward a Photographic Theory of Cel Animation -- 3. Pars Pro Toto: Character Animation and the Work of the Anonymous Artist -- 4. The Multiplication of Traces: Xerographic Reproduction and One Hundred and One Dalmatians -- Conclusion: The Labor of Looking -- Notes -- Bibliography -- Index
- Document LIN Search class: ['rest']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A756328888.jsonld | Estimation of the long-run food price equilibrium in Germany, the U.S. and Europe | In this thesis, so far insufficiently considered characteristics of long-run equilibriums in food markets are investigated. For this purpose, multivariate time series methodologies, which were developed for the estimation of long-run relationships by allowing for causality and convergence, are employed. In three essays, the proposed procedures are applied to food prices in Germany, the United States and Europe. The long-run equilibrium is defined as a state of an economic system (e.g. a market), to which the variables of the system revert as a consequence of economic mechanisms after being ... | [
"['oek']",
"['mat']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Estimation of the long-run food price equilibrium in Germany, the U.S. and Europe
- Document Abstract: In this thesis, so far insufficiently considered characteristics of long-run equilibriums in food markets are investigated. For this purpose, multivariate time series methodologies, which were developed for the estimation of long-run relationships by allowing for causality and convergence, are employed. In three essays, the proposed procedures are applied to food prices in Germany, the United States and Europe. The long-run equilibrium is defined as a state of an economic system (e.g. a market), to which the variables of the system revert as a consequence of economic mechanisms after being ...
- Document LIN Search class: ['oek'], ['mat']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1655568620.jsonld | Die Regierung der Gesundheit : Fragmente einer Genealogie liberaler Gouvernementalität | What is behind our health-related decisions? Discourses on health around middle-class self-practice, medical management, and the political technologies of the 19th century. Michel Foucault suchte bereits 1983 nach den Rationalitäten, die unseren gesundheitlichen Wahlentscheidungen zu Grunde liegen. Diese Frage stellt sich heute noch dringender, bedenkt man den neoliberalen Wandel von Gesundheitsdiskursen in den letzten Jahrzehnten. Diese Diskurse finden ihre Vorfahren in der religiösen und bürgerlichen Selbstpraxis sowie in der ärztlichen Praxis der Beratung und Überzeugung. Irene Poczka betrachtet diese als Regierungsweisen, die schließlich auch die politischen Techniken beeinflussten, mit denen die Gesundheit der Bevölkerungen reguliert werden sollte. Sie stellt fest: Im Europa des 19. Jahrhunderts lassen sich überall diskursive Fragmente einer Genealogie liberalen Regierens von Gesundheit ausmachen. | [
"['meda']",
"['his']",
"['sow']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Die Regierung der Gesundheit : Fragmente einer Genealogie liberaler Gouvernementalität
- Document Abstract: What is behind our health-related decisions? Discourses on health around middle-class self-practice, medical management, and the political technologies of the 19th century. Michel Foucault suchte bereits 1983 nach den Rationalitäten, die unseren gesundheitlichen Wahlentscheidungen zu Grunde liegen. Diese Frage stellt sich heute noch dringender, bedenkt man den neoliberalen Wandel von Gesundheitsdiskursen in den letzten Jahrzehnten. Diese Diskurse finden ihre Vorfahren in der religiösen und bürgerlichen Selbstpraxis sowie in der ärztlichen Praxis der Beratung und Überzeugung. Irene Poczka betrachtet diese als Regierungsweisen, die schließlich auch die politischen Techniken beeinflussten, mit denen die Gesundheit der Bevölkerungen reguliert werden sollte. Sie stellt fest: Im Europa des 19. Jahrhunderts lassen sich überall diskursive Fragmente einer Genealogie liberalen Regierens von Gesundheit ausmachen.
- Document LIN Search class: ['meda'], ['his'], ['sow']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A773153705.jsonld | A critical assessment of the socio-economic reintegration process of ex-combatants ten years after the war in Sierra Leone | This study examines the current socio-economic status of the ex-combatants 10 years after the conflict in Sierra Leone. It examines the job opportunities, political space, relationship with community members, challenges faced, social networks involved in, relationship with former colleagues, access to land and other issues that are significant in the reintegration process of ex-combatants. It further studies the national socio-economic environment and how ex-combatants are faring in the overall post-war recovery process in Sierra Leone. Special focus lies on the Disarmament, Demobilization and Reintegration of Ex-Combatants (DDR) programme which was part of the Lome Peace Agreement signed in 1999. The study also comes up with recommendations as to how the challenges currently faced by ex-combatants could be overcome. | [
"['sow']",
"['his']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: A critical assessment of the socio-economic reintegration process of ex-combatants ten years after the war in Sierra Leone
- Document Abstract: This study examines the current socio-economic status of the ex-combatants 10 years after the conflict in Sierra Leone. It examines the job opportunities, political space, relationship with community members, challenges faced, social networks involved in, relationship with former colleagues, access to land and other issues that are significant in the reintegration process of ex-combatants. It further studies the national socio-economic environment and how ex-combatants are faring in the overall post-war recovery process in Sierra Leone. Special focus lies on the Disarmament, Demobilization and Reintegration of Ex-Combatants (DDR) programme which was part of the Lome Peace Agreement signed in 1999. The study also comes up with recommendations as to how the challenges currently faced by ex-combatants could be overcome.
- Document LIN Search class: ['sow'], ['his']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A871821672.jsonld | Erklärung der Resignationstendenz von Lehrkräften durch individuelle Tätigkeits- und Kompetenzprofile und bildungspolitische Rahmenbedingungen | Teachers play an important role for children’s success at school as well as for the implementation and effectiveness of education policy reforms. However, in the national and international context the teaching profession belongs to those professions with a particularly high psychological strain, which can manifest itself in long-term incapacities to work as well as in poor teaching and a bad school climate. The study analyses if teachers’ resignative tendencies, which play an important role in the development of burnout symptoms, can be explained through individual and education policy factors and which aspects are more decisive. The theoretical explanatory model of teachers’ resignative tendencies is tested using structural equation modelling. The analyses show that individual as well as education policy factors explain teachers’ resignative tendencies to a certain extent, whereby the perceived school climate and teachers’ activity and competency profiles play a particularly important role. <engl.> Lehrkräfte allgemein- und berufsbildender Schulen nehmen eine zentrale Rolle für den schulischen Erfolg von Kindern und Jugendlichen sowie für die Umsetzung und Wirksamkeit bildungspolitischer Reformen ein. National wie international zählt der Lehrerberuf jedoch zu den Berufen mit besonders hohem, insbesondere psychischem Belastungspotential, welches sich in Arbeitsunfähigkeiten sowie einem qualitativ schlechteren Unterricht und Schulklima äußern kann. Im Rahmen der Arbeit wird analysiert, ob die Resignationstendenz von Lehrkräften, die eine entscheidende Rolle für die Entstehung des Burnout-Syndroms spielt, durch individuelle sowie bildungspolitische und schulische Faktoren erklärt werden kann und welche Aspekte dabei eine wichtigere Rolle spielen. Das theoretische Erklärungsmodell der Resignationstendenz von Lehrkräften wird mittels Strukturgleichungsanalysen überprüft. Diese zeigen, dass sowohl individuelle als auch bildungspolitische Faktoren die Resignationstendenz zu einem gewissen Teil erklären, wobei das wahrgenommene Schulklima und die Tätigkeits- und Kompetenzprofile der Lehrkräfte eine besonders wichtige Rolle spielen. <dt.> | [
"['pae']",
"['oek']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Erklärung der Resignationstendenz von Lehrkräften durch individuelle Tätigkeits- und Kompetenzprofile und bildungspolitische Rahmenbedingungen
- Document Abstract: Teachers play an important role for children’s success at school as well as for the implementation and effectiveness of education policy reforms. However, in the national and international context the teaching profession belongs to those professions with a particularly high psychological strain, which can manifest itself in long-term incapacities to work as well as in poor teaching and a bad school climate. The study analyses if teachers’ resignative tendencies, which play an important role in the development of burnout symptoms, can be explained through individual and education policy factors and which aspects are more decisive. The theoretical explanatory model of teachers’ resignative tendencies is tested using structural equation modelling. The analyses show that individual as well as education policy factors explain teachers’ resignative tendencies to a certain extent, whereby the perceived school climate and teachers’ activity and competency profiles play a particularly important role. <engl.> Lehrkräfte allgemein- und berufsbildender Schulen nehmen eine zentrale Rolle für den schulischen Erfolg von Kindern und Jugendlichen sowie für die Umsetzung und Wirksamkeit bildungspolitischer Reformen ein. National wie international zählt der Lehrerberuf jedoch zu den Berufen mit besonders hohem, insbesondere psychischem Belastungspotential, welches sich in Arbeitsunfähigkeiten sowie einem qualitativ schlechteren Unterricht und Schulklima äußern kann. Im Rahmen der Arbeit wird analysiert, ob die Resignationstendenz von Lehrkräften, die eine entscheidende Rolle für die Entstehung des Burnout-Syndroms spielt, durch individuelle sowie bildungspolitische und schulische Faktoren erklärt werden kann und welche Aspekte dabei eine wichtigere Rolle spielen. Das theoretische Erklärungsmodell der Resignationstendenz von Lehrkräften wird mittels Strukturgleichungsanalysen überprüft. Diese zeigen, dass sowohl individuelle als auch bildungspolitische Faktoren die Resignationstendenz zu einem gewissen Teil erklären, wobei das wahrgenommene Schulklima und die Tätigkeits- und Kompetenzprofile der Lehrkräfte eine besonders wichtige Rolle spielen. <dt.>
- Document LIN Search class: ['pae'], ['oek']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1824383940.jsonld | Synthesis of polycyclic heteroaromatic hydrocarbons by Pd-catalyzed cross-coupling reactions, alkyne carbonyl metathesis and acid mediated cycloisomerization | The present work deals with the synthesis of polycyclic heteroaromatic hydrocarbons based on functionalization of halogenated pyridine derivatives. Various pyrrolo[1,2-a][1,6]naphthyridines, (benzo-)thieno[3,2-f]quinoline , (benzo-)thieno[3,2-f]isoquinoline and 5- and 6-azaindoles were successfully developed based on sequential site- and regioselective Pd-catalyzed C–C and C–N coupling reactions, alkyne carbonyl metathesis and Brønsted acid mediated cycloisomerization. Selected synthesized final products were studied using UV and fluorescence spectroscopy to determine the optical properties.<eng> Die Arbeit beschäftigt sich mit der Synthese von polyzyklischen heteroaromatischen Kohlenwasserstoffen durch Funktionalisierung von halogenierten Pyridinderivaten.Verschiedene Pyrrolo[1,2-a][1,6]naphthyridine, (Benzo- )thieno[3,2-f]chinolin, (Benzo-)thieno[3,2-f]isochinolin, 5- und 6-Azaindole wurden erfolgreich durch regioselektive Pdkatalysierte C–C und C–N Kopplungsreaktionen, Alkin-Carbonyl-Metathese und Brønsted-Säure-vermittelte Cycloisomerisierungen entwickelt.Einige Syntheseprodukte wurden mittels UV- und Fluoreszenzspektroskopie untersucht, um die optischen Eigenschaften zu bestimmen..<ger> | [
"['che']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Synthesis of polycyclic heteroaromatic hydrocarbons by Pd-catalyzed cross-coupling reactions, alkyne carbonyl metathesis and acid mediated cycloisomerization
- Document Abstract: The present work deals with the synthesis of polycyclic heteroaromatic hydrocarbons based on functionalization of halogenated pyridine derivatives. Various pyrrolo[1,2-a][1,6]naphthyridines, (benzo-)thieno[3,2-f]quinoline , (benzo-)thieno[3,2-f]isoquinoline and 5- and 6-azaindoles were successfully developed based on sequential site- and regioselective Pd-catalyzed C–C and C–N coupling reactions, alkyne carbonyl metathesis and Brønsted acid mediated cycloisomerization. Selected synthesized final products were studied using UV and fluorescence spectroscopy to determine the optical properties.<eng> Die Arbeit beschäftigt sich mit der Synthese von polyzyklischen heteroaromatischen Kohlenwasserstoffen durch Funktionalisierung von halogenierten Pyridinderivaten.Verschiedene Pyrrolo[1,2-a][1,6]naphthyridine, (Benzo- )thieno[3,2-f]chinolin, (Benzo-)thieno[3,2-f]isochinolin, 5- und 6-Azaindole wurden erfolgreich durch regioselektive Pdkatalysierte C–C und C–N Kopplungsreaktionen, Alkin-Carbonyl-Metathese und Brønsted-Säure-vermittelte Cycloisomerisierungen entwickelt.Einige Syntheseprodukte wurden mittels UV- und Fluoreszenzspektroskopie untersucht, um die optischen Eigenschaften zu bestimmen..<ger>
- Document LIN Search class: ['che']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A785332928.jsonld | Integrative methods for reconstruction of dynamic networks in chondrogenesis | Application of human mesenchymal stem cells represents a promising approach in the field of regenerative medicine. Specific stimulation can give rise to chondrocytes, osteocytes or adipocytes. Investigation of the underlying biological processes which induce the observed cellular differentiation is essential to efficiently generate specific tissues for therapeutic purposes. Upon treatment with diverse stimuli, gene expression levels of cultivated human mesenchymal stem cells were monitored using time series microarray experiments for the three lineages. Application of gene network inference is a common approach to identify the regulatory dependencies among a set of investigated genes. This thesis applies the NetGenerator V2.0 tool, which is capable to deal with multiple time series data, which investigates the effect of multiple external stimuli. The applied model is based on a system of linear ordinary differential equations, whose parameters are optimised to reproduce the given time series datasets. Several procedures in the inference process were adapted in this new version in order to allow for the integration of multiple datasets. Network inference was applied on in silico network examples as well as on multi-experiment microarray data of mesenchymal stem cells. The resulting chondrogenesis model was evaluated on the basis of several features including the model adaptation to the data, total number of connections, proportion of connections associated with prior knowledge and the model stability in a resampling procedure. Altogether, NetGenerator V2.0 has provided an automatic and efficient way to integrate experimental datasets and to enhance the interpretability and reliability of the resulting network. In a second chondrogenesis model, the miRNA and mRNA time series data were integrated for the purpose of network inference. One hypothesis of the model was verified by experiments, which demonstrated the negative effect of miR-524-5p on downstream genes. | [
"['bio']",
"['meda']",
"['mat']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Integrative methods for reconstruction of dynamic networks in chondrogenesis
- Document Abstract: Application of human mesenchymal stem cells represents a promising approach in the field of regenerative medicine. Specific stimulation can give rise to chondrocytes, osteocytes or adipocytes. Investigation of the underlying biological processes which induce the observed cellular differentiation is essential to efficiently generate specific tissues for therapeutic purposes. Upon treatment with diverse stimuli, gene expression levels of cultivated human mesenchymal stem cells were monitored using time series microarray experiments for the three lineages. Application of gene network inference is a common approach to identify the regulatory dependencies among a set of investigated genes. This thesis applies the NetGenerator V2.0 tool, which is capable to deal with multiple time series data, which investigates the effect of multiple external stimuli. The applied model is based on a system of linear ordinary differential equations, whose parameters are optimised to reproduce the given time series datasets. Several procedures in the inference process were adapted in this new version in order to allow for the integration of multiple datasets. Network inference was applied on in silico network examples as well as on multi-experiment microarray data of mesenchymal stem cells. The resulting chondrogenesis model was evaluated on the basis of several features including the model adaptation to the data, total number of connections, proportion of connections associated with prior knowledge and the model stability in a resampling procedure. Altogether, NetGenerator V2.0 has provided an automatic and efficient way to integrate experimental datasets and to enhance the interpretability and reliability of the resulting network. In a second chondrogenesis model, the miRNA and mRNA time series data were integrated for the purpose of network inference. One hypothesis of the model was verified by experiments, which demonstrated the negative effect of miR-524-5p on downstream genes.
- Document LIN Search class: ['bio'], ['meda'], ['mat']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A690060165.jsonld | Towards ferrocyne and benzyne [pi]-complexes | (pi6-aryne)tricarbonylchromium(0), ferrocyne, anionic thia-Fries rearrangement, ferrocene derivates, photochemical reactions, transannular stereoinduction. - (Pi6-Arin)tricarbonylchromium(0), Ferrocin, anionische thia-Fries Umlagerung, Ferrocenderivate, photochemische Reaktionen, interannulare Stereoinduktion | [
"['che']",
"['cet']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Towards ferrocyne and benzyne [pi]-complexes
- Document Abstract: (pi6-aryne)tricarbonylchromium(0), ferrocyne, anionic thia-Fries rearrangement, ferrocene derivates, photochemical reactions, transannular stereoinduction. - (Pi6-Arin)tricarbonylchromium(0), Ferrocin, anionische thia-Fries Umlagerung, Ferrocenderivate, photochemische Reaktionen, interannulare Stereoinduktion
- Document LIN Search class: ['che'], ['cet']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1010583662.jsonld | Savanna dynamics under extreme conditions : Insights from a mathematical model | Savannas cover a broad geographical range across continents and are a biome best described by a mix of herbaceous and woody plants. The former create a more or less continuous layer while the latter should be sparse enough to leave an open canopy. What has long intrigued ecologists is how these two competing plant life forms of vegetation coexist. Initially attributed to resource competition, coexistence was considered the stable outcome of a root niche differentiation between trees and grasses. The importance of environmental factors became evident later, when data from moister environments demonstrated that tree cover was often lower than what the rainfall conditions would allow for. Our current understanding relies on the interaction of competition and disturbances in space and time. Hence, the influence of grazing and fire and the corresponding feedbacks they generate have been keenly investigated. Grazing removes grass cover, initiating a self-reinforcing process propagating tree cover expansion. This is known as the… | [
"['bio']",
"['hor']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Savanna dynamics under extreme conditions : Insights from a mathematical model
- Document Abstract: Savannas cover a broad geographical range across continents and are a biome best described by a mix of herbaceous and woody plants. The former create a more or less continuous layer while the latter should be sparse enough to leave an open canopy. What has long intrigued ecologists is how these two competing plant life forms of vegetation coexist. Initially attributed to resource competition, coexistence was considered the stable outcome of a root niche differentiation between trees and grasses. The importance of environmental factors became evident later, when data from moister environments demonstrated that tree cover was often lower than what the rainfall conditions would allow for. Our current understanding relies on the interaction of competition and disturbances in space and time. Hence, the influence of grazing and fire and the corresponding feedbacks they generate have been keenly investigated. Grazing removes grass cover, initiating a self-reinforcing process propagating tree cover expansion. This is known as the…
- Document LIN Search class: ['bio'], ['hor']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A668155701.jsonld | Modification of polysialic acid towards scaffolds for tissue engineering and synthesis of sialic acid derivatives | Tissue engineering, polysialic acid, sialic acid, 3D-scaffold. - Polysialinsäure, Sialinsäure, 3D-Gerüstmaterial | [
"['med']",
"['meda']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Modification of polysialic acid towards scaffolds for tissue engineering and synthesis of sialic acid derivatives
- Document Abstract: Tissue engineering, polysialic acid, sialic acid, 3D-scaffold. - Polysialinsäure, Sialinsäure, 3D-Gerüstmaterial
- Document LIN Search class: ['med'], ['meda']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A77857072X.jsonld | The Northeast Greenland Margin : tectonic evolution | The Norwegian-Greenland Sea (NGS) is an area of increasing interest. Here, the North Atlantic Current continues the Gulf Stream into the NGS. The warm ocean current plays an important role for the world's climate and influences the environment of the global Earth system. Calculations of climate models for the future based on the tectonic evolution of the NGS in the past. Based on few geoscientific data, the tectonic evolution of the NGS and the NE Greenland margin remains controversial. In the summer of 2009, the Alfred Wegener Institute acquired geophysical data - two seismic refraction lines as well as gravity data, measured in parallel to the seismic refraction lines - along the NE Greenland margin (Boreas Basin and offshore Kong Oscar Fjord (KOF)) during the ARK-XXIV/3 expedition. In addition, further gravity data (Arctic Gravity Project) were available and used within this study. Summarising the results, we could develop crustal models for the Boreas Basin and offshore KOF, using the seismic refraction data and the gravity data. Furthermore, a complex 3D gravity model of the NE Greenland margin was calculated, using the crustal models and further published data as boundary conditions. Following our conclusions, the structure of thin oceanic crust (3 km crustal thickness, absence of oceanic layer 3) in the Boreas Basin and along the ultraslow spreading Knipovich Ridge is more heterogeneous than previously thought. For the accretion of 9 km thick oceanic crust offshore KOF, the rift history of NE Greenland (extensive rifting before continental breakup) is more important than higher mantle temperatures caused by the Iceland Hotspot. Therefore, the Iceland Hotspot has smaller influence on the oceanic crustal accretion than previously thought. This might be further indicated by a 3 km thick high-velocity lower crust below the continent-ocean transition zone of KOF which is formed by enhanced melt generation along the nearby Jan Mayen Fracture Zone. | [
"['geo']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: The Northeast Greenland Margin : tectonic evolution
- Document Abstract: The Norwegian-Greenland Sea (NGS) is an area of increasing interest. Here, the North Atlantic Current continues the Gulf Stream into the NGS. The warm ocean current plays an important role for the world's climate and influences the environment of the global Earth system. Calculations of climate models for the future based on the tectonic evolution of the NGS in the past. Based on few geoscientific data, the tectonic evolution of the NGS and the NE Greenland margin remains controversial. In the summer of 2009, the Alfred Wegener Institute acquired geophysical data - two seismic refraction lines as well as gravity data, measured in parallel to the seismic refraction lines - along the NE Greenland margin (Boreas Basin and offshore Kong Oscar Fjord (KOF)) during the ARK-XXIV/3 expedition. In addition, further gravity data (Arctic Gravity Project) were available and used within this study. Summarising the results, we could develop crustal models for the Boreas Basin and offshore KOF, using the seismic refraction data and the gravity data. Furthermore, a complex 3D gravity model of the NE Greenland margin was calculated, using the crustal models and further published data as boundary conditions. Following our conclusions, the structure of thin oceanic crust (3 km crustal thickness, absence of oceanic layer 3) in the Boreas Basin and along the ultraslow spreading Knipovich Ridge is more heterogeneous than previously thought. For the accretion of 9 km thick oceanic crust offshore KOF, the rift history of NE Greenland (extensive rifting before continental breakup) is more important than higher mantle temperatures caused by the Iceland Hotspot. Therefore, the Iceland Hotspot has smaller influence on the oceanic crustal accretion than previously thought. This might be further indicated by a 3 km thick high-velocity lower crust below the continent-ocean transition zone of KOF which is formed by enhanced melt generation along the nearby Jan Mayen Fracture Zone.
- Document LIN Search class: ['geo']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A663597463.jsonld | Optimization of resonances for multilayer x-ray resonators | Resonances in open systems can be described by eigenvalue problems with a radiation condition at infinity and arise in various fields including acoustics, classical mechanics, quantum mechanics, and x-ray physics. This thesis focusses on the optimization of resonances for multilayer x-ray resonators which consist of several layers and support certain resonant states. These resonant states can be excited by x-ray beams under special grazing angles of incidence (corresponding to resonant frequencies of the system) leading to a very high field enhancement inside the system compared to the incident field. X-ray resonators or waveguides can be used for filtering, guiding, and concentration of x-rays, which is for example useful in nanoscale x-ray structure analysis and x-ray imaging. The multilayer structures can be characterized by the refractive index n. We want to find a function n for which the field enhancement in the multilayer structure for a resonant angle of incidence is maximized subject to side constraints on n. For the optimization problem we use an objective function involving complex resonances and corresponding resonance functions. Analytic expressions for the derivatives of resonances and resonance functions with respect to n are derived using perturbation theory of linear operators. As a side product, approximation formulas for the reflectivity are obtained, in particular a mathematical justification for the widely used kinematic approximation. Higher order Taylor approximations and Padé approximations lead to significant improvements of the standard approximation formulas, especially close to the critical angle. We explain how the optimization problem can be discretized and finish with numerical computation leading to improved multilayer x-ray resonators for several situations. | [
"['phy']",
"['mat']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Optimization of resonances for multilayer x-ray resonators
- Document Abstract: Resonances in open systems can be described by eigenvalue problems with a radiation condition at infinity and arise in various fields including acoustics, classical mechanics, quantum mechanics, and x-ray physics. This thesis focusses on the optimization of resonances for multilayer x-ray resonators which consist of several layers and support certain resonant states. These resonant states can be excited by x-ray beams under special grazing angles of incidence (corresponding to resonant frequencies of the system) leading to a very high field enhancement inside the system compared to the incident field. X-ray resonators or waveguides can be used for filtering, guiding, and concentration of x-rays, which is for example useful in nanoscale x-ray structure analysis and x-ray imaging. The multilayer structures can be characterized by the refractive index n. We want to find a function n for which the field enhancement in the multilayer structure for a resonant angle of incidence is maximized subject to side constraints on n. For the optimization problem we use an objective function involving complex resonances and corresponding resonance functions. Analytic expressions for the derivatives of resonances and resonance functions with respect to n are derived using perturbation theory of linear operators. As a side product, approximation formulas for the reflectivity are obtained, in particular a mathematical justification for the widely used kinematic approximation. Higher order Taylor approximations and Padé approximations lead to significant improvements of the standard approximation formulas, especially close to the critical angle. We explain how the optimization problem can be discretized and finish with numerical computation leading to improved multilayer x-ray resonators for several situations.
- Document LIN Search class: ['phy'], ['mat']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1040806309.jsonld | Deutsche Direktinvestitionen in Indien : Motive, regionale Verteilung und Effekte | Direktinvestitionen, Wirtschaftsreformen in Indien, Wissenstransfer. - FDI, economic reforms in India, spillover | [
"['oek']",
"['sow']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Deutsche Direktinvestitionen in Indien : Motive, regionale Verteilung und Effekte
- Document Abstract: Direktinvestitionen, Wirtschaftsreformen in Indien, Wissenstransfer. - FDI, economic reforms in India, spillover
- Document LIN Search class: ['oek'], ['sow']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A779005716.jsonld | Nicht-adiabatische Halbleitereinzelelektronenpumpe unter Magnetfeldeinfluss | Quantenpunkt, Einzelladungstransport, Einzelelektronenpumpe, SET-Pumpe, Neudefinition Ampere, Präzisionsstrommessung. - Quantum dot, single-electron transport, single-electron pump, SET-pump, re-definition of the Ampere, precision current measurement | [
"['phy']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Nicht-adiabatische Halbleitereinzelelektronenpumpe unter Magnetfeldeinfluss
- Document Abstract: Quantenpunkt, Einzelladungstransport, Einzelelektronenpumpe, SET-Pumpe, Neudefinition Ampere, Präzisionsstrommessung. - Quantum dot, single-electron transport, single-electron pump, SET-pump, re-definition of the Ampere, precision current measurement
- Document LIN Search class: ['phy']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1817741071.jsonld | Pollinators and ecosystem services in an oil palm transformation landscape | Insect pollination is an economically important ecosystem service that depends heavily on wild pollinators. Landscape transformation caused by conversion to agriculture threatens habitats of wild pollinators, reducing their potential to provide ecosystem services. The landscape in Jambi Province, Sumatra, Indonesia, is an example of a region undergoing landscape transformation, from biodiverse natural forests, to intermediate land uses such as fallow shrubland and jungle rubber, to monospecific oil palm plantations. My dissertation explores how transitions between these land uses impact pol... | [
"['bio']",
"['hor']",
"['cet']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Pollinators and ecosystem services in an oil palm transformation landscape
- Document Abstract: Insect pollination is an economically important ecosystem service that depends heavily on wild pollinators. Landscape transformation caused by conversion to agriculture threatens habitats of wild pollinators, reducing their potential to provide ecosystem services. The landscape in Jambi Province, Sumatra, Indonesia, is an example of a region undergoing landscape transformation, from biodiverse natural forests, to intermediate land uses such as fallow shrubland and jungle rubber, to monospecific oil palm plantations. My dissertation explores how transitions between these land uses impact pol...
- Document LIN Search class: ['bio'], ['hor'], ['cet']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1737595702.jsonld | Utilization of alternative phosphorus resources by regenerative agriculture practice based on mycorrhizal fungi and biostimulants for restoration of Lake Chamo watershed, Ethiopia | Climate change, soil degradation, shrinking biodiversity, low agricultural production and fossil phosphate resources increasingly impede food security in Sub-Saharan Africa. In this conceptual work, a holistic system for the productive restoration of degraded soil and water resources is developed, based on principles of humus-forming, regenerative agriculture and organic soil additives of bone and wood biochar as alternative fertilizer and structuring materials as well as biostimulatory plant additives for enhancement of plant and crop growth. In entirety, healthy soil life in general and mycorrhizal fungi in specific are promoted as the essential foundation of fertile, productive soil. Klimawandel, Bodendegradierung, sinkende Biodiversität, geringe landwirtschaftliche Produktivität und fossile Phosphatreserven gefährden zunehmend die Ernährungssicherheit in Sub-Sahara Afrika. In dieser konzeptionellen Arbeit wird ein ganzheitliches Gesamtsystem zur produktiven Restaurierung von degradierten Boden- und Wasserressourcen entwickelt, basierend auf Ansätzen der humus-aufbauenden Landwirtschaft mit organischen Bodenzusatzstoffen (Knochen- und Holzkohle als alternative Dünge- bzw. Strukturmaterialien) sowie Pflanzenadditive mit wachstumsfördernder Wirkung. In der Gesamtheit wird ein gesundes Bodenleben im generellen und Mykorrhiza-Bodenpilze im speziellen gefördert, als elementare Basis für fruchtbaren, leistungsfähigen Boden. | [
"['hor']",
"['geo']",
"['cet']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Utilization of alternative phosphorus resources by regenerative agriculture practice based on mycorrhizal fungi and biostimulants for restoration of Lake Chamo watershed, Ethiopia
- Document Abstract: Climate change, soil degradation, shrinking biodiversity, low agricultural production and fossil phosphate resources increasingly impede food security in Sub-Saharan Africa. In this conceptual work, a holistic system for the productive restoration of degraded soil and water resources is developed, based on principles of humus-forming, regenerative agriculture and organic soil additives of bone and wood biochar as alternative fertilizer and structuring materials as well as biostimulatory plant additives for enhancement of plant and crop growth. In entirety, healthy soil life in general and mycorrhizal fungi in specific are promoted as the essential foundation of fertile, productive soil. Klimawandel, Bodendegradierung, sinkende Biodiversität, geringe landwirtschaftliche Produktivität und fossile Phosphatreserven gefährden zunehmend die Ernährungssicherheit in Sub-Sahara Afrika. In dieser konzeptionellen Arbeit wird ein ganzheitliches Gesamtsystem zur produktiven Restaurierung von degradierten Boden- und Wasserressourcen entwickelt, basierend auf Ansätzen der humus-aufbauenden Landwirtschaft mit organischen Bodenzusatzstoffen (Knochen- und Holzkohle als alternative Dünge- bzw. Strukturmaterialien) sowie Pflanzenadditive mit wachstumsfördernder Wirkung. In der Gesamtheit wird ein gesundes Bodenleben im generellen und Mykorrhiza-Bodenpilze im speziellen gefördert, als elementare Basis für fruchtbaren, leistungsfähigen Boden.
- Document LIN Search class: ['hor'], ['geo'], ['cet']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1662464215.jsonld | Application of amine transaminases in the chemoenzymatic synthesis of chiral amines using isopropylamine as amine donor | Amine transaminases are versatile biocatalysts for the production of pharmaceutically and agrochemically relevant chiral amines. They represent an environmentally benign alternative to waste intensive transition metal catalysed synthesis strategies, especially because of their high stereoselectivity and robustness. Therefore, they have been frequently used in the (chemo)enzymatic synthesis of amines and/or became attractive targets for enzyme engineering especially in the last decade, mainly in order to enlarge their substrate scope. Certainly, one of the most notable examples of amine transaminase engineering is the manufacturing of the anti-diabetic drug Sitagliptin in large scale after several rounds of protein engineering. Thereby, the target amine was produced in asymmetric synthesis mode which is the most convenient and favored route to a target chiral amine, starting from the corresponding ketone. The choice of the amine donor is highly relevant for reaction design in terms of economical and thermodynamic considerations. For instance, the use of alanine as the natural amine donor is one of the most common strategies for the amination of target ketones but needs the involvement of auxiliary enzymes to shift the reaction equilibrium towards product formation. In fact, isopropylamine is probably one of the most favored donor molecules since it is cheap and achiral but it is supposed to be accepted only by a limited number of amine transaminases. This thesis focusses on ... Asymmetric synthesis, Chemo-enzymatic synthesis, Chiral amines, Isopropylamine, Protein engineering, Transaminases | [
"['che']",
"['bio']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Application of amine transaminases in the chemoenzymatic synthesis of chiral amines using isopropylamine as amine donor
- Document Abstract: Amine transaminases are versatile biocatalysts for the production of pharmaceutically and agrochemically relevant chiral amines. They represent an environmentally benign alternative to waste intensive transition metal catalysed synthesis strategies, especially because of their high stereoselectivity and robustness. Therefore, they have been frequently used in the (chemo)enzymatic synthesis of amines and/or became attractive targets for enzyme engineering especially in the last decade, mainly in order to enlarge their substrate scope. Certainly, one of the most notable examples of amine transaminase engineering is the manufacturing of the anti-diabetic drug Sitagliptin in large scale after several rounds of protein engineering. Thereby, the target amine was produced in asymmetric synthesis mode which is the most convenient and favored route to a target chiral amine, starting from the corresponding ketone. The choice of the amine donor is highly relevant for reaction design in terms of economical and thermodynamic considerations. For instance, the use of alanine as the natural amine donor is one of the most common strategies for the amination of target ketones but needs the involvement of auxiliary enzymes to shift the reaction equilibrium towards product formation. In fact, isopropylamine is probably one of the most favored donor molecules since it is cheap and achiral but it is supposed to be accepted only by a limited number of amine transaminases. This thesis focusses on ... Asymmetric synthesis, Chemo-enzymatic synthesis, Chiral amines, Isopropylamine, Protein engineering, Transaminases
- Document LIN Search class: ['che'], ['bio']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A617229325.jsonld | The Martian moon Phobos : a geodetic analysis of its motion, orientation, shape, and physical parameters | Mars is accompanied by two small natural satellites. Deimos, the smaller of the two, is orbiting at a greater distance from Mars while Phobos revolves around the planet at a mean altitude of approximately 6,000km with respect to the Martian surface, deep in the gravity field of the planet. An in-depth study of the irregular shaped moon Phobos was commenced due to remaining questions on its orbital motion, shape, and physical parameters based on new high resolution images of the Super Resolution Channel (SRC) and the High Resolution Stereo Camera (HRSC) which are part of the European Mars Express Mission (MEX). Parameters of ephemerides models were questioned after the finding of large discrepancies of Phobos' position to astrometric observations. During the course of this study astrometric measurements were made in fly-by images of Phobos and through observations of Phobos' shadow on the Martian surface. While results of the latter analysis led to largely scattered differences compared to orbit prediction models with high uncertainties, the fly-by observations were in agreement with the ephemerides models within the error bands. Offsets were rather consistent and systematic indicating that Phobos is ahead of its predicted position by approximately 2 km. To be able to model the irregular shape of Phobos by means of different techniques - namely a digital terrain model and a model based on spherical harmonic functions - a new global control point network was established. The 665 object point coordinates with respect to the Phobos body-fixed coordinate frame were determined through observations in 53 SRC and 16 Viking Orbiter images ... | [
"['rest']",
"['phy']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: The Martian moon Phobos : a geodetic analysis of its motion, orientation, shape, and physical parameters
- Document Abstract: Mars is accompanied by two small natural satellites. Deimos, the smaller of the two, is orbiting at a greater distance from Mars while Phobos revolves around the planet at a mean altitude of approximately 6,000km with respect to the Martian surface, deep in the gravity field of the planet. An in-depth study of the irregular shaped moon Phobos was commenced due to remaining questions on its orbital motion, shape, and physical parameters based on new high resolution images of the Super Resolution Channel (SRC) and the High Resolution Stereo Camera (HRSC) which are part of the European Mars Express Mission (MEX). Parameters of ephemerides models were questioned after the finding of large discrepancies of Phobos' position to astrometric observations. During the course of this study astrometric measurements were made in fly-by images of Phobos and through observations of Phobos' shadow on the Martian surface. While results of the latter analysis led to largely scattered differences compared to orbit prediction models with high uncertainties, the fly-by observations were in agreement with the ephemerides models within the error bands. Offsets were rather consistent and systematic indicating that Phobos is ahead of its predicted position by approximately 2 km. To be able to model the irregular shape of Phobos by means of different techniques - namely a digital terrain model and a model based on spherical harmonic functions - a new global control point network was established. The 665 object point coordinates with respect to the Phobos body-fixed coordinate frame were determined through observations in 53 SRC and 16 Viking Orbiter images ...
- Document LIN Search class: ['rest'], ['phy']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1843619059.jsonld | Investigation of ancient proteins in archaeological material | Although several studies have positively identified dairy proteins from ancient dental calculus, other dietary protein identifications are exceedingly rare. The manuscripts included in this thesis include the identification of 20 different dietary proteins that could be taxonomically identified to the species level from 10 different species. One of our primary goals for this thesis was to evaluate any potential biases in our dietary protein recovery, and to gain a deeper understanding of the factors that influence dietary protein preservation within dental calculus. Although our sample sizes are small, we did find evidence of biases in the types of proteins we have recovered thus far. All proteins identified were potential allergens with IgE binding sites, low monomer molecular weight, resistance to changes in pH and temperature, and resistance to degradation through enzymatic proteolysis. The identified proteins primarily had functions in host defense or storage. | [
"['meda']",
"['bio']",
"['rest']",
"['che']",
"['pae']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Investigation of ancient proteins in archaeological material
- Document Abstract: Although several studies have positively identified dairy proteins from ancient dental calculus, other dietary protein identifications are exceedingly rare. The manuscripts included in this thesis include the identification of 20 different dietary proteins that could be taxonomically identified to the species level from 10 different species. One of our primary goals for this thesis was to evaluate any potential biases in our dietary protein recovery, and to gain a deeper understanding of the factors that influence dietary protein preservation within dental calculus. Although our sample sizes are small, we did find evidence of biases in the types of proteins we have recovered thus far. All proteins identified were potential allergens with IgE binding sites, low monomer molecular weight, resistance to changes in pH and temperature, and resistance to degradation through enzymatic proteolysis. The identified proteins primarily had functions in host defense or storage.
- Document LIN Search class: ['meda'], ['bio'], ['rest'], ['che'], ['pae']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1681400332.jsonld | Diakonie ist Kirche : zur Notwendigkeit der Genese einer Diakoniekirche | In the Protestant understanding, a church has to renew itself continuously. In the 21st century, Protestant churches have a high reputation but few bonding forces. The results of surveys among churchmen are obvious: The perception of the church in society derives from welfare and social work (diaconia). In times of a post-traditional people’s church, the question arises of whether the church will be a church of welfare and social work (diaconia) in the future. Reflecting on the countrywide disappearance of churches in Eastern Germany, Matthias Fichtmüller formu-lates the thesis that in future entrepreneurial welfare and social work will take over the tasks of churches. He outlines the conflicts between the institutional church and welfare and social work, and develops a nuanced understanding of church membership. Welfare and social work are not replacing the institutional church but are an enriching addition to it. They are a place for people who cannot find a home in the national churches any more. Nach evangelischem Verständnis muss sich die Kirche beständig verändern. Die evangelischen Kirchen besitzen im 21. Jahrhundert hohe Reputation, doch geringe Bindungskräfte. Die Ergebnisse der Kirchenmitgliedschaftsuntersuchungen (KMU) sprechen seit Jahrzehnten eine eindeutige Sprache: Die Wahrnehmung der Kirche in der Gesellschaft erfolgt über diakonische Aktivitäten. Im postvolkskirchlichen Kontext stellt sich die Frage, ob die Kirche der Zukunft eine Diakoniekirche ist. In Reflexion der zunehmenden flächendeckenden Entkirchlichung in Ostdeutschland stellt Matthias Fichtmüller die These auf, dass die unternehmerische Diakonie künftig Aufgaben der Kirche übernehmen kann. Dabei werden die Konflikte zwischen verfasster Kirche und Diakonie beleuchtet und ein neues, gestuftes Mitgliedschaftsverständnis entwickelt. Diakoniekirche löst nicht die verfasste Kirche ab, doch sie ist ein bereicherndes Additiv zu den bisherigen kirchlichen Strukturen. In ihr können sich Menschen wiederfinden, die in den Landeskirchen keine Heimat haben. | [
"['rel']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Diakonie ist Kirche : zur Notwendigkeit der Genese einer Diakoniekirche
- Document Abstract: In the Protestant understanding, a church has to renew itself continuously. In the 21st century, Protestant churches have a high reputation but few bonding forces. The results of surveys among churchmen are obvious: The perception of the church in society derives from welfare and social work (diaconia). In times of a post-traditional people’s church, the question arises of whether the church will be a church of welfare and social work (diaconia) in the future. Reflecting on the countrywide disappearance of churches in Eastern Germany, Matthias Fichtmüller formu-lates the thesis that in future entrepreneurial welfare and social work will take over the tasks of churches. He outlines the conflicts between the institutional church and welfare and social work, and develops a nuanced understanding of church membership. Welfare and social work are not replacing the institutional church but are an enriching addition to it. They are a place for people who cannot find a home in the national churches any more. Nach evangelischem Verständnis muss sich die Kirche beständig verändern. Die evangelischen Kirchen besitzen im 21. Jahrhundert hohe Reputation, doch geringe Bindungskräfte. Die Ergebnisse der Kirchenmitgliedschaftsuntersuchungen (KMU) sprechen seit Jahrzehnten eine eindeutige Sprache: Die Wahrnehmung der Kirche in der Gesellschaft erfolgt über diakonische Aktivitäten. Im postvolkskirchlichen Kontext stellt sich die Frage, ob die Kirche der Zukunft eine Diakoniekirche ist. In Reflexion der zunehmenden flächendeckenden Entkirchlichung in Ostdeutschland stellt Matthias Fichtmüller die These auf, dass die unternehmerische Diakonie künftig Aufgaben der Kirche übernehmen kann. Dabei werden die Konflikte zwischen verfasster Kirche und Diakonie beleuchtet und ein neues, gestuftes Mitgliedschaftsverständnis entwickelt. Diakoniekirche löst nicht die verfasste Kirche ab, doch sie ist ein bereicherndes Additiv zu den bisherigen kirchlichen Strukturen. In ihr können sich Menschen wiederfinden, die in den Landeskirchen keine Heimat haben.
- Document LIN Search class: ['rel']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1023439034.jsonld | The entrepreneurial culture : network advantage within Chinese and Irish software firms | 1. Entrepreneurship and business culture -- 2. Institutional environment in city software clusters -- 3. Culture of software entrepreneurship -- 4. A theory of cultural capital -- 5. Personal networks, social networks and new firms -- 6. Network advantage and successful firms -- 7. Future growth in Chinese and Irish software The Entrepreneurial Culture highlights the subtle yet powerful influence of national cultural heritage on entrepreneurship ventures, using an alternative and fresh approach to explore the entrepreneurial culture of Chinese and Irish software firms. This book presents a unique analysis of entrepreneurship theory development, along with a single industry, cross-national study of entrepreneurship illustrating the impact of values from contrasting cultures | [
"['oek']",
"['pae']",
"['sow']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: The entrepreneurial culture : network advantage within Chinese and Irish software firms
- Document Abstract: 1. Entrepreneurship and business culture -- 2. Institutional environment in city software clusters -- 3. Culture of software entrepreneurship -- 4. A theory of cultural capital -- 5. Personal networks, social networks and new firms -- 6. Network advantage and successful firms -- 7. Future growth in Chinese and Irish software The Entrepreneurial Culture highlights the subtle yet powerful influence of national cultural heritage on entrepreneurship ventures, using an alternative and fresh approach to explore the entrepreneurial culture of Chinese and Irish software firms. This book presents a unique analysis of entrepreneurship theory development, along with a single industry, cross-national study of entrepreneurship illustrating the impact of values from contrasting cultures
- Document LIN Search class: ['oek'], ['pae'], ['sow']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1682489043.jsonld | Learning from reliable and unreliable speakers | As a way to bypass the need for the many iterations of individual experiences required for trial and error learning, humans and several non-human animal species have evolved a capacity to rely on information provided by others. Non-human animals typically learn from conspecifics through stimulus enhancement or emulation learning, using the same tools a conspecific used to obtain the same goal or trying to replicate the outcome of certain behavior. Human children on the other hand do not just focus on the outcome when learning from others. They pay a lot of attention to the teacher and the t... | [
"['bio']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Learning from reliable and unreliable speakers
- Document Abstract: As a way to bypass the need for the many iterations of individual experiences required for trial and error learning, humans and several non-human animal species have evolved a capacity to rely on information provided by others. Non-human animals typically learn from conspecifics through stimulus enhancement or emulation learning, using the same tools a conspecific used to obtain the same goal or trying to replicate the outcome of certain behavior. Human children on the other hand do not just focus on the outcome when learning from others. They pay a lot of attention to the teacher and the t...
- Document LIN Search class: ['bio']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A837491932.jsonld | Herstellung, Charakterisierung und Anwendung einer rekombinanten Patchoulolsynthese zur biokatalytischen Herstellung von Sesquiterpenen | Sesquiterpene, Sesquiterpensynthasen, Biokatalyse, Enzymtechnik, Patchouliöl, Patchoulol. - Sesquiterpenes, sesquiterpene synthases, biocatalysis, enzyme technology, patchouli oil | [
"['che']",
"['cet']",
"['bio']",
"['hor']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Herstellung, Charakterisierung und Anwendung einer rekombinanten Patchoulolsynthese zur biokatalytischen Herstellung von Sesquiterpenen
- Document Abstract: Sesquiterpene, Sesquiterpensynthasen, Biokatalyse, Enzymtechnik, Patchouliöl, Patchoulol. - Sesquiterpenes, sesquiterpene synthases, biocatalysis, enzyme technology, patchouli oil
- Document LIN Search class: ['che'], ['cet'], ['bio'], ['hor']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1657191265.jsonld | Classical Statistical Mechanics with Nested Sampling | This thesis develops a nested sampling algorithm into a black box tool for directly calculating the partition function, and thus the complete phase diagram of a material, from the interatomic potential energy function. It represents a significant step forward in our ability to accurately describe the finite temperature properties of materials. In principle, the macroscopic phases of matter are related to the microscopic interactions of atoms by statistical mechanics and the partition function. In practice, direct calculation of the partition function has proved infeasible for realistic models of atomic interactions, even with modern atomistic simulation methods. The thesis also shows how the output of nested sampling calculations can be processed to calculate the complete PVT (pressure–volume–temperature) equation of state for a material, and applies the nested sampling algorithm to calculate the pressure–temperature phase diagrams of aluminium and a model binary alloy. Introduction -- A Primer in Probability -- Phase Space Probability Distributions for Various External Conditions -- Relating Probability Density Functions to the Behaviour of Systems -- The Strategy of Nested Sampling -- Nested Sampling for Materials -- Equations of State -- Parallelising Nested Sampling -- Hamiltonian Monte Carlo for the Canonical Distribution -- Hamiltonian Monte Carlo for Nested Sampling -- Conclusion of Thesis and Further Work. | [
"['phy']",
"['mat']",
"['fer']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Classical Statistical Mechanics with Nested Sampling
- Document Abstract: This thesis develops a nested sampling algorithm into a black box tool for directly calculating the partition function, and thus the complete phase diagram of a material, from the interatomic potential energy function. It represents a significant step forward in our ability to accurately describe the finite temperature properties of materials. In principle, the macroscopic phases of matter are related to the microscopic interactions of atoms by statistical mechanics and the partition function. In practice, direct calculation of the partition function has proved infeasible for realistic models of atomic interactions, even with modern atomistic simulation methods. The thesis also shows how the output of nested sampling calculations can be processed to calculate the complete PVT (pressure–volume–temperature) equation of state for a material, and applies the nested sampling algorithm to calculate the pressure–temperature phase diagrams of aluminium and a model binary alloy. Introduction -- A Primer in Probability -- Phase Space Probability Distributions for Various External Conditions -- Relating Probability Density Functions to the Behaviour of Systems -- The Strategy of Nested Sampling -- Nested Sampling for Materials -- Equations of State -- Parallelising Nested Sampling -- Hamiltonian Monte Carlo for the Canonical Distribution -- Hamiltonian Monte Carlo for Nested Sampling -- Conclusion of Thesis and Further Work.
- Document LIN Search class: ['phy'], ['mat'], ['fer']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A639561187.jsonld | Chemische und chemoenzymatische Synthesezugänge zu neuen Ansamitocinderivaten | Ansamitocine, Mutasynthese, Huisgen-Cycloaddition, Negishi-Kupplung. - Ansamitocins, mutasynthesis, Huisgen-cycloaddition, Negishi-coupling | [
"['meda']",
"['che']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Chemische und chemoenzymatische Synthesezugänge zu neuen Ansamitocinderivaten
- Document Abstract: Ansamitocine, Mutasynthese, Huisgen-Cycloaddition, Negishi-Kupplung. - Ansamitocins, mutasynthesis, Huisgen-cycloaddition, Negishi-coupling
- Document LIN Search class: ['meda'], ['che']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1788386965.jsonld | Entrepreneurship: the role of gender, perceptions, and institutions | hile women's evolving contribution to entrepreneurship is irrefutable, in almost all nations, gender disparity is an existing reality of entrepreneurship. Social and economic outcomes make women entrepreneurship an important area for scholars and governments. In attempts to find reasons for this gender disparity, academic scholars evaluated various factors and recognised perceptual variables as having outstanding explanatory value in understanding women's entrepreneurship. To advance our knowledge of gender disparity in entrepreneurship, the present study explores the influence of entrepreneurial perceptual variables on women's entrepreneurship and considers the critical role of country-level institutional contexts on the women's entrepreneurial propensity. Therefore, this study examines the impact of perceptual variables in different nations. It also offers connections between entrepreneurial perceptions, women entrepreneurship, and institutional contexts as a critical topic for future studies. Drawing on the importance of perceptual factors, this dissertation investigates whether and how their perception of entrepreneurial networks influences the individuals' decision to initiate a new venture. Prior scholars considered exposure to entrepreneurial role models as one of the most influential factors on the women's inclination towards entrepreneurship; thus, a systemized analysis makes it possible to identify existing research gaps related to this perception. Hence, to draw a clear picture of the relationship between entrepreneurial role models and entrepreneurship, this dissertation provides a systemized overview of prior studies. Subsequently, Chapter 2 structures the existing literature on entrepreneurial role models and reveals that past literature has focused on the different types of role models, the stage of life at which the exposure to role models occurs, and the context of the exposure. Current discourse argues that the women's lower access to entrepreneurial role models negatively influences their inclination towards entrepreneurship. Additionally, although the research on women entrepreneurship has proliferated in recent years, little is known about how entrepreneurial perceptual variables form women's propensity towards entrepreneurship in various institutional contexts. The work of Koellinger et al. (2013), hereafter KMS, is one of the most influential papers that investigated the influence of perceptual variables, and it showed that a lower rate of women entrepreneurship is associated with a lower level of their entrepreneurial network, perceived entrepreneurial capability, and opportunity evaluation and with a higher fear of entrepreneurial failure. Thus, this dissertation replicates the work of KMS. Chapter 3 explicitly investigates the influence of the above perceptions on women's entrepreneurial propensity. This research has drawn data from the Global Entrepreneurship Monitor, a cross-national individual-level data set (2001-2006) covering 236,556 individuals across 17 countries. The results of this chapter suggest that gender disparities in entrepreneurial propensity are conditioned by differences in entrepreneurial perceptual variables. Women's lower levels of perceived entrepreneurial capability, entrepreneurial role models and opportunity evaluation and their higher fear of failure lead to lower entrepreneurial propensity. To extend and generalise the relationship between perceptions and women's entrepreneurial propensity, in Chapter 4, two studies are conducted based on replicated research. Extension 1 generalises the results of KMS by using the same analysis on more recent data. Accordingly, this research implemented the same analysis on 372,069 individuals across the same countries (2011-2016). The recent data show that although gender disparity became significantly weaker, the gender gap is still in men's favour. However, similarly to the replicated study, this research revealed that perceptual factors explain a larger part of the gender disparity. To strengthen prior empirical evidence, in extension 2, utilising a sample of 1,029,863 individuals from 71 countries (2011-2016), the study conducted the same measures and analysis in a more global setting. By including developing countries, gender disparity in entrepreneurial propensity decreased significantly. The study revealed that the relative significance of the influences of perceptions' differs significantly across nations; however, perceptions have a worldwide effect. Moreover, this research found that the ratio of nascent women entrepreneurs in less developed countries to those in more developed nations is 2. More precisely, a higher level of economic development negatively influences the impact of perceptions on women's entrepreneurial propensity. Whereas prior scholars increasingly underlined the importance of perceptions in explaining a large part of gender disparities in entrepreneurship, most of the prior investigations focused on nascent (early-stage) entrepreneurship, and evidence on the relationship between perceptions and other types of self-employment, such as innovative entrepreneurship, is scant. Innovation is a confirmed key driver of a firm's sustainability, higher competitive capability, and growth. Therefore, Chapter 5 investigates the influence of perceptions on women's innovative entrepreneurship. The chapter points out that entrepreneurial perceptions are the main determinants of the women's decision to offer a new product or service. This chapter also finds that women's innovative entrepreneurship is associated with the country's specific economic setting. Overall, by underlining the critical role of institutional contexts, this dissertation provides considerable insights into the interaction between perceptions and women entrepreneurship, and its results have implications for policymakers and practitioners, who may find it helpful to consider women entrepreneurship in systemized challenges. Formal and informal barriers affect women's entrepreneurial perceptions and can differ from one country to the other. In this sense, it is crucial to design operational plans to mitigate formal and stereotypical challenges, and thus, more women will be able to start a business, particularly in developing countries in which women significantly comprise a smaller portion of the labour markets. This type of policy could write the "rules of the game" such that these rules enhance the women's propensity towards entrepreneurship. | [
"['oek']",
"['sow']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Entrepreneurship: the role of gender, perceptions, and institutions
- Document Abstract: hile women's evolving contribution to entrepreneurship is irrefutable, in almost all nations, gender disparity is an existing reality of entrepreneurship. Social and economic outcomes make women entrepreneurship an important area for scholars and governments. In attempts to find reasons for this gender disparity, academic scholars evaluated various factors and recognised perceptual variables as having outstanding explanatory value in understanding women's entrepreneurship. To advance our knowledge of gender disparity in entrepreneurship, the present study explores the influence of entrepreneurial perceptual variables on women's entrepreneurship and considers the critical role of country-level institutional contexts on the women's entrepreneurial propensity. Therefore, this study examines the impact of perceptual variables in different nations. It also offers connections between entrepreneurial perceptions, women entrepreneurship, and institutional contexts as a critical topic for future studies. Drawing on the importance of perceptual factors, this dissertation investigates whether and how their perception of entrepreneurial networks influences the individuals' decision to initiate a new venture. Prior scholars considered exposure to entrepreneurial role models as one of the most influential factors on the women's inclination towards entrepreneurship; thus, a systemized analysis makes it possible to identify existing research gaps related to this perception. Hence, to draw a clear picture of the relationship between entrepreneurial role models and entrepreneurship, this dissertation provides a systemized overview of prior studies. Subsequently, Chapter 2 structures the existing literature on entrepreneurial role models and reveals that past literature has focused on the different types of role models, the stage of life at which the exposure to role models occurs, and the context of the exposure. Current discourse argues that the women's lower access to entrepreneurial role models negatively influences their inclination towards entrepreneurship. Additionally, although the research on women entrepreneurship has proliferated in recent years, little is known about how entrepreneurial perceptual variables form women's propensity towards entrepreneurship in various institutional contexts. The work of Koellinger et al. (2013), hereafter KMS, is one of the most influential papers that investigated the influence of perceptual variables, and it showed that a lower rate of women entrepreneurship is associated with a lower level of their entrepreneurial network, perceived entrepreneurial capability, and opportunity evaluation and with a higher fear of entrepreneurial failure. Thus, this dissertation replicates the work of KMS. Chapter 3 explicitly investigates the influence of the above perceptions on women's entrepreneurial propensity. This research has drawn data from the Global Entrepreneurship Monitor, a cross-national individual-level data set (2001-2006) covering 236,556 individuals across 17 countries. The results of this chapter suggest that gender disparities in entrepreneurial propensity are conditioned by differences in entrepreneurial perceptual variables. Women's lower levels of perceived entrepreneurial capability, entrepreneurial role models and opportunity evaluation and their higher fear of failure lead to lower entrepreneurial propensity. To extend and generalise the relationship between perceptions and women's entrepreneurial propensity, in Chapter 4, two studies are conducted based on replicated research. Extension 1 generalises the results of KMS by using the same analysis on more recent data. Accordingly, this research implemented the same analysis on 372,069 individuals across the same countries (2011-2016). The recent data show that although gender disparity became significantly weaker, the gender gap is still in men's favour. However, similarly to the replicated study, this research revealed that perceptual factors explain a larger part of the gender disparity. To strengthen prior empirical evidence, in extension 2, utilising a sample of 1,029,863 individuals from 71 countries (2011-2016), the study conducted the same measures and analysis in a more global setting. By including developing countries, gender disparity in entrepreneurial propensity decreased significantly. The study revealed that the relative significance of the influences of perceptions' differs significantly across nations; however, perceptions have a worldwide effect. Moreover, this research found that the ratio of nascent women entrepreneurs in less developed countries to those in more developed nations is 2. More precisely, a higher level of economic development negatively influences the impact of perceptions on women's entrepreneurial propensity. Whereas prior scholars increasingly underlined the importance of perceptions in explaining a large part of gender disparities in entrepreneurship, most of the prior investigations focused on nascent (early-stage) entrepreneurship, and evidence on the relationship between perceptions and other types of self-employment, such as innovative entrepreneurship, is scant. Innovation is a confirmed key driver of a firm's sustainability, higher competitive capability, and growth. Therefore, Chapter 5 investigates the influence of perceptions on women's innovative entrepreneurship. The chapter points out that entrepreneurial perceptions are the main determinants of the women's decision to offer a new product or service. This chapter also finds that women's innovative entrepreneurship is associated with the country's specific economic setting. Overall, by underlining the critical role of institutional contexts, this dissertation provides considerable insights into the interaction between perceptions and women entrepreneurship, and its results have implications for policymakers and practitioners, who may find it helpful to consider women entrepreneurship in systemized challenges. Formal and informal barriers affect women's entrepreneurial perceptions and can differ from one country to the other. In this sense, it is crucial to design operational plans to mitigate formal and stereotypical challenges, and thus, more women will be able to start a business, particularly in developing countries in which women significantly comprise a smaller portion of the labour markets. This type of policy could write the "rules of the game" such that these rules enhance the women's propensity towards entrepreneurship.
- Document LIN Search class: ['oek'], ['sow']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A750026065.jsonld | The presence of the past in the novels of Toni Morrison | Hauptbeschreibung: After decades of research into the role of memory, trauma, and historiography in her work, to say that Toni Morrison's novels deal with the presence of the past may seem like a truism. But the complexity of Morrison's vision originates in her understanding of the nature of this past as both individual and collective. This study approaches Morrison's more recent novels on the basis of both literary analysis and sociological theory: drawing on the work of Pierre Bourdieu and Norbert Elias, it shows that the presence of the past in her work unfolds not only in images | [
"['lit']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: The presence of the past in the novels of Toni Morrison
- Document Abstract: Hauptbeschreibung: After decades of research into the role of memory, trauma, and historiography in her work, to say that Toni Morrison's novels deal with the presence of the past may seem like a truism. But the complexity of Morrison's vision originates in her understanding of the nature of this past as both individual and collective. This study approaches Morrison's more recent novels on the basis of both literary analysis and sociological theory: drawing on the work of Pierre Bourdieu and Norbert Elias, it shows that the presence of the past in her work unfolds not only in images
- Document LIN Search class: ['lit']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A671918125.jsonld | Involvement of two nitric oxide-associated genes, NOA1 and GSNOR, in Nicotiana attenuata's resistance to the specialist insect herbivore Manduca sexta | Nitric oxide-associated protein 1 (NOA1) is involved in various abiotic stress responses and is required for plant resistance to pathogen infections. The first chapter of this dissertation explores for the first time the role of NOA1 in plant-herbivore interactions. We created NOA1-silenced Nicotiana attenuata plants (irNaNOA1), which had highly decreased photosynthesis rates. We further examined plant defense traits against its specialist herbivore Manduca sexta by treating WT and irNaNOA1 plants with mechanical wounding and M. sexta oral secretions (OS). NOA1-silenced plants showed elevated levels of herbivory-induced jasmonic acid (JA), but decreased JA-isoleucine conjugate (JA-Ile) levels that did not result from compromised JAR (jasmonic acid resistant) activity in irNOA1 plants. Moreover, nitrogen-rich defensive compounds, nicotine and trypsin proteinase inhibitors (TPI), did not differ between WT and irNaNOA1 plants. In contrast, concentrations of most carbon-based defensive compounds were lower in these plants than in WT plants, although the levels of chlorogenic acid were not changed. Therefore, silencing NOA1 alters the allocation of carbon resources within the phenylpropanoid pathway. These data suggest the involvement of NOA1 in N. attenuata’s defense against M. sexta attack, and highlight its role in photosynthesis, and biosynthesis of jasmonates and secondary metabolites. | [
"['bio']",
"['che']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Involvement of two nitric oxide-associated genes, NOA1 and GSNOR, in Nicotiana attenuata's resistance to the specialist insect herbivore Manduca sexta
- Document Abstract: Nitric oxide-associated protein 1 (NOA1) is involved in various abiotic stress responses and is required for plant resistance to pathogen infections. The first chapter of this dissertation explores for the first time the role of NOA1 in plant-herbivore interactions. We created NOA1-silenced Nicotiana attenuata plants (irNaNOA1), which had highly decreased photosynthesis rates. We further examined plant defense traits against its specialist herbivore Manduca sexta by treating WT and irNaNOA1 plants with mechanical wounding and M. sexta oral secretions (OS). NOA1-silenced plants showed elevated levels of herbivory-induced jasmonic acid (JA), but decreased JA-isoleucine conjugate (JA-Ile) levels that did not result from compromised JAR (jasmonic acid resistant) activity in irNOA1 plants. Moreover, nitrogen-rich defensive compounds, nicotine and trypsin proteinase inhibitors (TPI), did not differ between WT and irNaNOA1 plants. In contrast, concentrations of most carbon-based defensive compounds were lower in these plants than in WT plants, although the levels of chlorogenic acid were not changed. Therefore, silencing NOA1 alters the allocation of carbon resources within the phenylpropanoid pathway. These data suggest the involvement of NOA1 in N. attenuata’s defense against M. sexta attack, and highlight its role in photosynthesis, and biosynthesis of jasmonates and secondary metabolites.
- Document LIN Search class: ['bio'], ['che']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A1652049533.jsonld | Spaces for Jihād : Indian Muslims and Conceptions of Citizenship | This thesis deals with the question of how Indian Muslims make use of the spaces and channels granted by the democratic framework to accommodate their Islamic identity with the secular one, and to what extent their Islamic identity is conceived (or perceived) as either conducive or conflicting with the political setting they live in. By comparing between a majority and minority setting, an analysis of how the socio-political context shapes citizens’ perceptions of multiple variables such as their sense of political efficacy, agency, conception of citizenship rights and belief in democracy is undertaken. | [
"['rel']",
"['his']",
"['sow']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Spaces for Jihād : Indian Muslims and Conceptions of Citizenship
- Document Abstract: This thesis deals with the question of how Indian Muslims make use of the spaces and channels granted by the democratic framework to accommodate their Islamic identity with the secular one, and to what extent their Islamic identity is conceived (or perceived) as either conducive or conflicting with the political setting they live in. By comparing between a majority and minority setting, an analysis of how the socio-political context shapes citizens’ perceptions of multiple variables such as their sense of political efficacy, agency, conception of citizenship rights and belief in democracy is undertaken.
- Document LIN Search class: ['rel'], ['his'], ['sow']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A848109902.jsonld | Essays on consumers' perceptions and valuations of health-enhancing attributes in food products | The complexity and controversy of research outcomes in the field of consumer perceptions and valuations of health-enhancing attributes in food products motivated this dissertation. This controversy arises from unclear connection between income levels and the demand for functional foods, disputed values of health-enhancing attributes for consumers, and increasing complexity in consumers’ decision-making. Thus, the research presented in this dissertation aimed at developing evidence on consumers’ perceptions and valuations of health-enhancing attributes in food products, advancing the methodological approach for studying consumer food choices, and summarizing existing knowledge on the topic. The originality of this dissertation arises from: (i) systematic review of the literature employing meta-analysis; (ii) modified methodological approach to the analysis of the empirical data; (iii)specific empirical evidence from an understudied region (Russia); and (iv) comparative analysis of qualitative data in a cross-cultural context. willingness to pay; experimental auction; health-enhancing food; functional food; random utility; reference point; meta-analysis; trust Zahlungsbereitschaft; experimentelle Auktion; gesundheitsfördernde Lebensmittel; funktionelle Lebensmittel; random utility Modelle; reference points effects Modelle; Metaanalyse; Vertrauen Die Komplexität und Kontroversen über Verbraucherwahrnehmung und Bewertung gesundheitsfördernder Eigenschaften von Lebensmitteln motivierten diese Dissertation. Die Kontroversen umfassen die nicht eindeutige Verbindung zwischen Einkommensniveau und der Nachfrage nach funktionellen Lebensmitteln, umstrittenen Nutzen gesundheitsfördernder Eigenschaften für den Konsumenten und eine steigende Komplexität in Verbraucherentscheidungen. Ziel dieser Dissertation ist es, neue empirische Evidenz in Bezug auf Verbraucherwahrnehmung und Bewertung gesundheitsfördernden Eigenschaften von Lebensmitteln zu liefern, die Methodik zur Untersuchung von Verbraucherentscheidungen weiter zu entwickeln und die bestehenden Kenntnisse zusammenzufassen. Die Dissertation trägt zur bestehenden Literatur in den folgenden Punkte bei: (I) systematischer Review der Literatur mittels Metaanalyse; (II) Weiterentwicklung der Methodik für die Analyse empirischer Daten; (III) spezifische empirische Belege für eine bisher wenig untersuchte Region (Russland); und (IV) eine vergleichende Analyse qualitativer Daten in einem interkulturellen Kontext. | [
"['oek']",
"['sow']",
"['hor']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Essays on consumers' perceptions and valuations of health-enhancing attributes in food products
- Document Abstract: The complexity and controversy of research outcomes in the field of consumer perceptions and valuations of health-enhancing attributes in food products motivated this dissertation. This controversy arises from unclear connection between income levels and the demand for functional foods, disputed values of health-enhancing attributes for consumers, and increasing complexity in consumers’ decision-making. Thus, the research presented in this dissertation aimed at developing evidence on consumers’ perceptions and valuations of health-enhancing attributes in food products, advancing the methodological approach for studying consumer food choices, and summarizing existing knowledge on the topic. The originality of this dissertation arises from: (i) systematic review of the literature employing meta-analysis; (ii) modified methodological approach to the analysis of the empirical data; (iii)specific empirical evidence from an understudied region (Russia); and (iv) comparative analysis of qualitative data in a cross-cultural context. willingness to pay; experimental auction; health-enhancing food; functional food; random utility; reference point; meta-analysis; trust Zahlungsbereitschaft; experimentelle Auktion; gesundheitsfördernde Lebensmittel; funktionelle Lebensmittel; random utility Modelle; reference points effects Modelle; Metaanalyse; Vertrauen Die Komplexität und Kontroversen über Verbraucherwahrnehmung und Bewertung gesundheitsfördernder Eigenschaften von Lebensmitteln motivierten diese Dissertation. Die Kontroversen umfassen die nicht eindeutige Verbindung zwischen Einkommensniveau und der Nachfrage nach funktionellen Lebensmitteln, umstrittenen Nutzen gesundheitsfördernder Eigenschaften für den Konsumenten und eine steigende Komplexität in Verbraucherentscheidungen. Ziel dieser Dissertation ist es, neue empirische Evidenz in Bezug auf Verbraucherwahrnehmung und Bewertung gesundheitsfördernden Eigenschaften von Lebensmitteln zu liefern, die Methodik zur Untersuchung von Verbraucherentscheidungen weiter zu entwickeln und die bestehenden Kenntnisse zusammenzufassen. Die Dissertation trägt zur bestehenden Literatur in den folgenden Punkte bei: (I) systematischer Review der Literatur mittels Metaanalyse; (II) Weiterentwicklung der Methodik für die Analyse empirischer Daten; (III) spezifische empirische Belege für eine bisher wenig untersuchte Region (Russland); und (IV) eine vergleichende Analyse qualitativer Daten in einem interkulturellen Kontext.
- Document LIN Search class: ['oek'], ['sow'], ['hor']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A61599024X.jsonld | Studies on the molecular interactions of collagen type XVI : Part I: The role of collagen XVI in pathological disorders ; Part II: Extablishment of a retroviral mediated gene silencing model | Enth.: Part 1. The role of collagen XVI in pathological disorders. - Part 2. Establishment of a retroviral mediated gene silencing model | [
"['bio']",
"['meda']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Studies on the molecular interactions of collagen type XVI : Part I: The role of collagen XVI in pathological disorders ; Part II: Extablishment of a retroviral mediated gene silencing model
- Document Abstract: Enth.: Part 1. The role of collagen XVI in pathological disorders. - Part 2. Establishment of a retroviral mediated gene silencing model
- Document LIN Search class: ['bio'], ['meda']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A739268260.jsonld | A process model for customer relationship management system selection | CRM, system selection, system evaluation, case study research, process model, automotive industry. - System Auswahlprozess, Software Auswahl, Fallbeispiel Forschung, Prozessmodell, Automobilindustrie | [
"['oek']",
"['inf']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: A process model for customer relationship management system selection
- Document Abstract: CRM, system selection, system evaluation, case study research, process model, automotive industry. - System Auswahlprozess, Software Auswahl, Fallbeispiel Forschung, Prozessmodell, Automobilindustrie
- Document LIN Search class: ['oek'], ['inf']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
3A64341780X.jsonld | Dietary effects on the relationship between fatty acid profile, lipid peroxidation, antioxidant status, and quality in beef muscle | Two different experiments were carried out in order to investigate the influence of feeding n-3 and n-6 PUFA enriched diets on the relationship of lipid peroxidation and antioxidant status including fatty acid composition and quality in longissimus muscle from bulls. The lipid peroxidation extent in muscle depended on the antioxidant status offered by each diet. Antioxidant capacity of muscle was no affected by the diet using TEAC and FRAP assay. There was a combined effect of n-3 PUFA enriched diet and feeding restriction lipid peroxidation, and tenderness of longissimus muscle. | [
"['meda']",
"['pae']",
"['rest']"
] | <|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 30 May 2025
You are a highly skilled text processing assistant specialized in analyzing and extracting structured information from text. Your task is to identify entities relevant to a given domain and format the output consistently. You excel at understanding context, adhering to instructions, and providing accurate results. Your responses should be clear, concise, and follow any specified requirements, such as output format conventions.<|eot_id|><|start_header_id|>user<|end_header_id|>
### Act as:
You are a librarian and an expert in the GND (the integrated authority files):
Code Classification Number ... Definition Source URL
0 gnd:4003694-7 00 ... NaN NaN
1 gnd:4032393-6 00 ... Verknüpfe mit Anwendungsgebiet NaN
2 gnd:4038971-6 00 ... NaN NaN
3 gnd:4043744-9 00 ... Allgemeinbegriff, verknüpfe mit Anwendungsgebiet NaN
4 gnd:4048300-9 00 ... Etwas, was einer Sache ein bestimmtes (äußere... NaN
... ... ... ... ... ...
204734 gnd:7753641-1 36 ... NaN NaN
204735 gnd:7755608-2 36 ... NaN NaN
204736 gnd:7758731-5 36 ... NaN NaN
204737 gnd:7842847-6 36 ... NaN NaN
204738 gnd:1163295434 36 ... NaN https://www.airfix.com/uk-en/
[204739 rows x 9 columns]
You also have the knowledge of LIN Search classification:
- arc Architecture
- bau Civil engineering
- ber Mining
- bio Life Science
- cet Chemical and environmental engineering
- che Chemistry
- elt Electrical engineering
- fer Material science
- geo Earth science
- his History
- hor Horticulture
- inf Computer science
- jur Law
- lin Linguistics
- lit Literature Studies
- mas Mechanical engineering, energy technology
- mat Mathematics
- med Medical technology
- meda Medicine
- oek Economics
- pae Educational science
- phi Philosophy
- phy Physics
- rel Study of religions
- rest Other subjects
- sow Social sciences
- spo Sports science
- tec Engineering
- ver Traffic engineering
### Given the following details:
- Document Title: Dietary effects on the relationship between fatty acid profile, lipid peroxidation, antioxidant status, and quality in beef muscle
- Document Abstract: Two different experiments were carried out in order to investigate the influence of feeding n-3 and n-6 PUFA enriched diets on the relationship of lipid peroxidation and antioxidant status including fatty acid composition and quality in longissimus muscle from bulls. The lipid peroxidation extent in muscle depended on the antioxidant status offered by each diet. Antioxidant capacity of muscle was no affected by the diet using TEAC and FRAP assay. There was a combined effect of n-3 PUFA enriched diet and feeding restriction lipid peroxidation, and tenderness of longissimus muscle.
- Document LIN Search class: ['meda'], ['pae'], ['rest']
### Your task:
Using your expert knowledge in the conventional use of the GND, you are now tasked to assign **exactly 20** subject titles to documents according to the database of GND subject titles.
Your task is to annotate documents with GND subjects in JSON format based on their content (title and abstract). Use your knowledge of GND annotations and follow the established patterns from past training data.
1. Analyze the title, abstract and LIN Search class of a document and infer GND subject annotations.
2. Produce the output in structured JSON format, maintaining consistency with examples provided.
Rules:
- Always extract subjects from the core concepts mentioned in the title/abstract.
- Include synonyms, variant names, and related subjects in arrays.
- Follow the structure exactly as shown in the examples.
- Always quote the JSON format output between ```json and ```.
- No more than 20 alternate names is allowed for each subject.
- No more than 20 related subjects is allowed for each subject.
### Instructions:
1. Analyze the provided document to identify its core themes, topics, and concepts.
2. Select the most appropriate **20 unique GND subject titles** that align with the content, in the same style as the dataset you were trained on.
3. Rank the GND subject titles according to the relevance to the document, and the likelihood they would be assigned by an expert librarian.
4. Format the output as JSON, adhering to the structure provided below. For each of the subject titles, reply with the name of the subject titles, its names and related subjects in a list.
5. Make sure to complete the JSON output before you hit the maximum token limit, to ensure the correctness of the JSON format.
### Output example:
```json
{
"document_title": "Energie- und Lademanagement für eine CO2-neutralen Beladung von batterieelektrisch betriebenen Service-Fahrzeugen auf dem Flughafenvorfeld",
"assigned_subject_titles": [
{
"Code": "gnd-4014736-8",
"Name": "Energieversorgung",
"Alternate Name": ["Energie", "Energieversorgungssystem", "Energiesystem"],
"Related Subjects": ["Versorgung", "Energieerzeugung", "Energiewirtschaft"]
},
{
"Code": "gnd-4068598-6",
"Name": "Erneuerbare Energien",
"Alternate Name": ["Sanfte Energie", "Erneuerbare Energiequelle", "Regenerative Energiequelle", "Regenerative Energie", "Erneuerbare Energie", "Alternativenergie", "Alternativenergien", "Regenerative Energien", "Alternative Energiequelle", "Grüne Energie", "Green energy"],
"Related Subjects": ["Energiequelle", "Erneuerbare Ressourcen"]
},
...
]
}
```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.