Andrew Eells
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Andrew Eells has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Pascal Hitzler
Kansas State University
2 shared publications - Adrita Barua
Kansas State University, Manhattan, Kansas, USA
1 shared publication - Alicia Sheill
Michigan State Univ, MATRIX, E Lansing, MI USA
1 shared publication - Antrea Christou
Department of Engineering and Computer Science, Wright State University, Dayton, OH, USA
1 shared publication Brandon Dave
Wright State University
1 shared publication- Catherine Foley
Michigan State Univ, MATRIX, E Lansing, MI USA
1 shared publication
Latest Publications
- 17 March 2025
- Published by IOS Press
- p. 421-438
Ontology Population Using LLMs
Knowledge graphs (KGs) are increasingly utilized for data integration, representation, and visualization. While KG population is critical, it is often costly, especially when data must be extracted from unstructured text in natural language, which presents challenges, such as ambiguity and complex interpretations. Large Language Models (LLMs) offer promising capabilities for such tasks, excelling in natural language understanding and content generation. However, their tendency to “hallucinate” can produce inaccurate outputs. Despite these limitations, LLMs offer rapid and scalable processing of natural language data, and with prompt engineering and fine-tuning, they can approximate human-level performance in extracting and structuring data for KGs. This study investigates LLM effectiveness for the KG population, focusing on the Enslaved.org Hub Ontology. In this paper, we report that compared to the ground truth, LLM’s can extract ≈90% of triples, when provided a modular ontology as guidance in the prompts.
- 17 March 2025
- Published by IOS Press
- p. 421-438
Ontology Population Using LLMs
Knowledge graphs (KGs) are increasingly utilized for data integration, representation, and visualization. While KG population is critical, it is often costly, especially when data must be extracted from unstructured text in natural language, which presents challenges, such as ambiguity and complex interpretations. Large Language Models (LLMs) offer promising capabilities for such tasks, excelling in natural language understanding and content generation. However, their tendency to “hallucinate” can produce inaccurate outputs. Despite these limitations, LLMs offer rapid and scalable processing of natural language data, and with prompt engineering and fine-tuning, they can approximate human-level performance in extracting and structuring data for KGs. This study investigates LLM effectiveness for the KG population, focusing on the Enslaved.org Hub Ontology. In this paper, we report that compared to the ground truth, LLM’s can extract ≈90% of triples, when provided a modular ontology as guidance in the prompts.
- Open Access
- 24 June 2024
- Published by Elsevier in Journal of Web Semantics
- Vol. 82
Ontology design facilitating Wikibase integration — and a worked example for historical data
- 24 June 2024
- Published by Elsevier in Journal of Web Semantics
- Vol. 82
Open AccessOntology design facilitating Wikibase integration — and a worked example for historical data