Metraipolis › archive › dc_fb537994aa5c
LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text — arXiv:2609.31663
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31663
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:49:51.415Z
- SHA-256 of the archived text
5cc93c376894975ef83a470620449e6f9d0a3c531c14cf1b24971ca95a88ac54- Stable URL of this page
https://metraipolis.com/documento/dc_fb537994aa5c
How to cite
LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text — arXiv:2609.31663 — arXiv (en), https://arxiv.org/abs/2609.31663 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb537994aa5c (Metraipolis archive dc_fb537994aa5c, sha256 5cc93c376894975ef83a470620449e6f9d0a3c531c14cf1b24971ca95a88ac54)
BibTeX
@misc{dcfb537994aa5c,
title = {LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text — arXiv:2609.31663},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31663},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb537994aa5c; sha256 5cc93c376894975ef83a470620449e6f9d0a3c531c14cf1b24971ca95a88ac54},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31663. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Ontology-driven knowledge graph construction from industrial text remains challenging due to the domain specificity of documents, the scarcity of annotated resources, and the complexity of ontology engineering workflows. This paper presents and investigates the applicability of an ontology learning pipeline that combines compact open-source Large Language Models (LLMs), reusable prompting strategies, and open knowledge bases to support the extraction, structuring, enrichment, and evaluation of knowledge from textual corpora. The approach is tested and evaluated on a private French corpus of power-grid incident reports, using locally deployable open-source LLMs ranging from 7B to 32B parameters. Starting from unstructured reports, the approach extracts entities and relations, generates RDF triples, constructs related OWL ontology, enriches it using external knowledge sources, assesses the quality of the ontology, and subsequently constructs a populated knowledge graph grounded in the resulting ontology schema. Experiments on 80 manually annotated private reports show that schema-guided prompting significantly improves extraction quality, while quantized models provide an effective trade-off between performance and computational cost. These results demonstrate the feasibility of transforming domain-specific industrial text into ontology-based knowledge graphs using locally deployed open-source LLMs, while supporting the generalization of the extraction process through reusable prompting strategies. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.31663 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T21:27:08.359Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).