Enriching RDF Data with LLM Based Named Entity Recognition and Linking on Embedded Natural Language Annotations
Freund M, Dorsch R, Schmid SJ, Wehr T, Harth A (2025)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2025
Journal
Publisher: Springer
Series: Lecture Notes in Computer Science
City/Town: Cham
Book Volume: LNCS,volume 15459
Pages Range: 109-122
Conference Proceedings Title: Knowledge Graphs and Semantic Web
Event location: Paris
ISBN: 9783031812200
DOI: 10.1007/978-3-031-81221-7_8
Abstract
In this paper, we present a processing pipeline for transforming natural language annotations in RDF graphs into machine-readable and interoperable semantic annotations. The pipeline uses Named Entity Recognition (NER) and Entity Linking (EL) techniques based on a foundational Large Language Model (LLM), combined with a Knowledge Graph (KG) based knowledge injection approach for entity disambiguation and self-verification. Through a running example in the paper, we demonstrate that the pipeline can increase the number of semantic annotations in an RDF graph derived from information contained in natural language annotations. The evaluation of the proposed pipeline shows that the LLM-based NER approach produces results comparable to those of fine-tuned NER models. Furthermore, we show that the pipeline using a chain-of-thought prompting style with factual information retrieved via link traversal from an external KG achieves better entity disambiguation and linking than both a pipeline without chain-of-thought prompting and an approach relying only on information within the LLM.
Authors with CRIS profile
Michael Freund
Sebastian Josef Schmid Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme Thomas Wehr Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme Andreas Harth Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme
Sebastian Josef Schmid Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme Thomas Wehr Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme Andreas Harth Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme
Involved external institutions
Germany (DE)How to cite
APA:
Freund, M., Dorsch, R., Schmid, S.J., Wehr, T., & Harth, A. (2025). Enriching RDF Data with LLM Based Named Entity Recognition and Linking on Embedded Natural Language Annotations. In Knowledge Graphs and Semantic Web (pp. 109-122). Paris, FR: Cham: Springer.
MLA:
Freund, Michael, et al. "Enriching RDF Data with LLM Based Named Entity Recognition and Linking on Embedded Natural Language Annotations." Proceedings of the 6th International Conference, KGSWC 2024, Paris Cham: Springer, 2025. 109-122.
BibTeX: Download