Experiments with chatgpt for Llm-assisted knowledge graph engineering

experiments conducted as described in our publication "Llm-assisted knowledge graph engineering: Experiments with chatgpt" (Springer link/Arxiv.org link) by Meyer, Lars-Peter and Stadler, Claus and Frey, Johannes and Radtke, Norman and Junghanns, Kurt and Meissner, Roy and Dziwis, Gordian and Bulert, Kirill and Martin, Michael. Presented and Published at AI-Tomorrow, 29.+30. 6. 2023 Leipzig, Germany.

• Experiment 1: SPARQL Query Generation for a Custom Small Knowledge Graph
• Experiment 2: Token Counts for Knowledge Graphs Schemas
• Experiment 3: SPARQL Query Generation for the Mondial Knowledge Graph
• Experiment 4: Knowledge Extraction from Fact Sheets
• Experiment 5: Knowledge Graph Exploration

BibTex entry for the publication: bibtex @InProceedings{Meyer2023LLMassistedKnowledge, author = {Meyer, Lars-Peter and Stadler, Claus and Frey, Johannes and Radtke, Norman and Junghanns, Kurt and Meissner, Roy and Dziwis, Gordian and Bulert, Kirill and Martin, Michael}, title = {LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT}, booktitle = {First Working Conference on Artificial Intelligence Development for a Resilient and Sustainable Tomorrow (AITomorrow) 2023}, year = {2023}, editor = {Christian Zinke-Wehlmann and Julia Friedrich}, pages = {101-112}, series = {Informatik aktuell}, abstract = {Knowledge Graphs (KG) provide us with a structured, flexible, transparent, cross-system, and collaborative way of organizing our knowledge and data across various domains in society and industrial as well as scientific disciplines. KGs surpass any other form of representation in terms of effectiveness. However, Knowledge Graph Engineering (KGE) requires in-depth experiences of graph structures, web technologies, existing models and vocabularies, rule sets, logic, as well as best practices. It also demands a significant amount of work. Considering the advancements in large language models (LLMs) and their interfaces and applications in recent years, we have conducted comprehensive experiments with ChatGPT to explore its potential in supporting KGE. In this paper, we present a selection of these experiments and their results to demonstrate how ChatGPT can assist us in the development and management of KGs.}, archiveprefix = {arXiv}, comment = {Results: https://github.com/AKSW/AI-Tomorrow-2023-KG-ChatGPT-Experiments}, copyright = {Creative Commons Attribution 4.0 International}, doi = {10.1007/978-3-658-43705-3_8}, eprint = {2307.06917} }