# LLM-guided ontology construction from unstructured texts

Digest AI · Research · published 2026-09-29T04:00:00Z

Canonical: https://digestai.news/story/llm-guided-ontology-construction-from-unstructured-texts

## Summary

A new approach combines compact open-source Large Language Models (LLMs) with ontology learning to extract and structure knowledge from industrial text. This paper evaluates the method on a private French corpus of power-grid incident reports, using LLMs ranging from 7B to 32B parameters. The process extracts entities and relations, generates RDF triples, constructs an OWL ontology, enriches it with external sources, assesses its quality, and builds a populated knowledge graph grounded in the resulting schema. Experiments show that prompting strategies improve extraction quality while quantized models balance performance and computational cost. These results suggest using locally deployed open-source LLMs to transform domain-specific industrial text into ontology-based knowledge graphs, supporting generalization through reusable prompts.

## Key points

- Combines compact LLMs with ontology learning for text processing
- Evaluates approach on French power-grid incident reports corpus
- Improves extraction quality with schema-guided prompting and quantized models

## Why it matters

This research demonstrates the feasibility of transforming domain-specific industrial text into ontology-based knowledge graphs using locally deployed open-source LLMs, which could have significant implications for data management in industry sectors.

## Sources

1. [LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text](https://arxiv.org/abs/2609.31663) (arXiv cs.CL, 2026-09-29, primary source)

Part of the developing story: [LLMs Revolutionize Automated Knowledge Graph Construction](https://digestai.news/thread/researchers-propose-goal-driven-variant-categorization-using-llm) (2 stories)

## Cite

Digest AI, "LLM-guided ontology construction from unstructured texts", 29 September 2026, https://digestai.news/story/llm-guided-ontology-construction-from-unstructured-texts

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/llm-guided-ontology-construction-from-unstructured-texts.json