Triples-Driven Ontology Construction with LLMs for Urban Planning Compliance

Rania Bennetayeb, Rania Bennetayeb, Giuseppe Berio, Nicolas Bechet, Albert Murienne

2025

Abstract

Ensuring compliance with urban planning regulations requires both semantic precision and fully interpretable decision processes. In this paper, we present a semi-automated methodology that combines the flexibility of large language models with the rigour of Semantic Web technologies to develop an urban planning ontology from regulatory texts. First, the paper presents a systematic evaluation of eight state-of-the-art large language models on the WebNLG dataset for semantic triple extraction task, using few-shot and chain-of-thought prompting. It then discusses the engineering of a domain-adapted prompt. The resulting triples are partially validated through a two-step procedure that takes into account the topological properties of an underlying graph (corresponding to a raw version of a knowledge graph) and the assessment of Human domain experts.

Paper Citation

in Harvard Style

Bennetayeb R., Berio G., Bechet N. and Murienne A. (2025). Triples-Driven Ontology Construction with LLMs for Urban Planning Compliance. In Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD; ISBN 978-989-758-769-6, SciTePress, pages 184-191. DOI: 10.5220/0013838700004000

in Bibtex Style

@conference{keod25,
author={Rania Bennetayeb and Giuseppe Berio and Nicolas Bechet and Albert Murienne},
title={Triples-Driven Ontology Construction with LLMs for Urban Planning Compliance},
booktitle={Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD},
year={2025},
pages={184-191},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013838700004000},
isbn={978-989-758-769-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD
TI - Triples-Driven Ontology Construction with LLMs for Urban Planning Compliance
SN - 978-989-758-769-6
AU - Bennetayeb R.
AU - Berio G.
AU - Bechet N.
AU - Murienne A.
PY - 2025
SP - 184
EP - 191
DO - 10.5220/0013838700004000
PB - SciTePress