An LLM-based Multi-agent Framework for Publishing RDF Views into Enterprise Knowledge Graphs

• Asley Lioba Universidade Federal do Ceará (UFC) https://orcid.org/0009-0004-1162-9397
• José Renato S. Freitas Universidade Federal do Ceará (UFC)
• Tulio Vidal Rolim Instituto Federal do Piauí (IFPI) https://orcid.org/0000-0002-6662-4938
• Vânia M. P. Vidal Universidade Federal do Ceará (UFC) https://orcid.org/0000-0002-9370-8598

DOI: https://doi.org/10.5753/sbbd.2026.249654

Resumo

The publication of heterogeneous data into Enterprise Knowledge Graphs (EKGs) remains challenging due to schema matching, semantic inconsistencies, and the effort required to create mappings and target ontology. This paper presents a metadata-driven multi-agent framework based on Large Language Models (LLMs) for generating RDF views from data sources. The framework orchestrates agents for schema extraction, ontology bootstrapping-refining, semantic mapping generation, and RDF materialization tasks. The approach leverages metadata, represented through the Vocabulary of Semantic Views (VoSV) into a data design pattern (DDP SV), as in-context learning to support explainability, governance, and incremental publication. As a way to perform a preliminary evaluation of this framework, a case study using Brazilian public government purchases data sources demonstrates the feasibility of automating RDF view publication.

Palavras-chave: Enterprise Knowledge Graphs, Large Language Models, Multi-Agent Systems, RDF View Generation, Semantic Data Publishing

Referências

Alzahrani, S. and O’Sullivan, D. (2025). Guiding llm generated mappings with lifecyclebased metadata: An early evaluation.

Arenas-Guerrero, J., Chaves-Fraga, D., Toledo, J., Pérez, M. S., and Corcho, O. (2024). Morph-KGC: Scalable knowledge graph materialization with mapping partitions. Semantic Web, 15(1):1–20.

Conrado, R. C., Campos, E. M., Traina Jr, C., Traina, A. J., and Cazzolato, M. T. (2025). From tables to graphs with clinicoatlas: Leveraging llms to support modeling and mining knowledge graphs. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 64–69. SBC.

da Silva, G. M., de Armas, E. M., Saieg, P., de Castro, R. A., Coqueiro, T. D., Lemos, M., and Castro, L. C. (2025). Llms na geração de mapeamentos semânticos: Experimento no domínio de plantas industriais. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 449–458. SBC.

Hofer, M., Frey, J., and Rahm, E. (2024). Towards self-configuring knowledge graph construction pipelines using llms-a case study with rml. In Fifth International Workshop on Knowledge Graph Construction@ ESWC2024.

Kommineni, V. K., König-Ries, B., and Samuel, S. (2024). From human experts to machines: An llm supported approach to ontology and knowledge graph construction. arXiv preprint arXiv:2403.08345.

Mavridis, A., Tegos, S., Anastasiou, C., Papoutsoglou, M., and Meditskos, G. (2025). Large language models for intelligent rdf knowledge graph construction: results from medical ontology mapping. Frontiers in Artificial Intelligence, 8:1546179.

Vidal, V., Freitas, R., Arruda, N., Casanova, M. A., and Renso, C. (2024). A data design pattern for building and exploring semantic views of enterprise knowledge graphs. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados, pages 1–13, Porto Alegre, RS, Brasil. SBC.