CITATION.cff

cff-version: 1.2.0
message: "If you use this software, please cite it using the metadata from this file."
title: "LLM-Driven Ontology Construction for Enterprise Knowledge Graphs"
type: software
abstract: >-
  Enterprise Knowledge Graphs have become essential for unifying heterogeneous data and enforcing
  semantic governance. However, the construction of their underlying ontologies remains a
  resource-intensive, manual process that relies heavily on domain expertise. This project
  introduces OntoEKG, an LLM-driven pipeline designed to accelerate the generation of
  domain-specific ontologies from unstructured enterprise data. The approach decomposes the
  modelling task into two distinct phases: an extraction module that identifies core classes and
  properties, and an entailment module that logically structures these elements into a hierarchy
  before serialising them into standard RDF. Addressing the significant lack of comprehensive
  benchmarks for end-to-end ontology construction, a new evaluation dataset derived from documents
  across the Data, Finance, and Logistics sectors is adopted. Experimental results highlight both
  the potential and the challenges of this approach, achieving a fuzzy-match F1-score of 0.724 in
  the Data domain while revealing limitations in scope definition and hierarchical reasoning.
authors:
  - family-names: "Oyewale"
    given-names: "Abdulsobur"
  - family-names: "Soru"
    given-names: "Tommaso"
repository-code: "https://github.com/LiberAI/OntoEKG"
keywords:
  - enterprise knowledge graphs
  - ontology construction
  - ontology learning
  - knowledge graphs
  - rdf
  - owl
  - llm
  - semantic modeling
preferred-citation:
  type: article
  authors:
    - family-names: "Oyewale"
      given-names: "Abdulsobur"
    - family-names: "Soru"
      given-names: "Tommaso"
  title: "LLM-Driven Ontology Construction for Enterprise Knowledge Graphs"
  journal: "20th International Conference on Semantic Computing (ICSC)"
  year: 2026