Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

DOI: http://dx.doi.org/10.15439/2026F9943

Citation: Eliot Bytyçi, Arianit Kurti, Bekim Gashi (2026). LLM-Assisted Expansion of Winery Ontologies with Kosovo Agritech Context. In M. Bolanowski, M. Ganzha, M. Grzegorowski, L. Maciaszek, M. Paprzycki, A. Paszkiewicz, D. Ślęzak (eds), Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS). ACSIS, Vol. 47, pages 483–486.

Full text

Abstract. Ontology engineering is an intensive and costly process, requiring domain expertise, ontology design skills and also manually intervening in the end. With the recent advantages in Large Language Models, new possibilities have been opened to automate or at least expedite the ontology creation, by enabling their localization first of all, extraction and alignment. Thus, this motivated us to explore development of Kosovo Winery Ontology, being a semantic framework for Kosovo's emerging wine industry. Our approach integrates three existing ontologies: W3C wine ontology, Davis Wine ontology and Wine Cloud ontology, with extension of local data context. The resulting ontology should serve as schema for the Agritech project, a project that will use precision agriculture in Kosovo. Moreover, it will serve as a case study in LLM assisted ontology engineering, demonstrating further the fostering of digital transformation in agriculture.

References

1. H. Babaei Giglou, J. D’Souza, and S. Auer, “LLMs4OL 2024 Overview: The 1st Large Language Models for Ontology Learning Challenge,” in Open Conference Proceedings, vol. 4, 2024. [Online]. Available: https://www.tib-op.org/ojs/index.php/ocp/article/view/2473
2. M. J. Saeedizade and E. Blomqvist, “Navigating Ontology Development with Large Language Models,” in The Semantic Web – ESWC 2024 (Lecture Notes in Computer Science), Springer, 2024. [Online]. Available: https://doi.org/10.1007/978-3-031-60626-7_8
3. S. El-Sappagh et al., “Ontology-grounded knowledge graphs for mitigating hallucinations in LLM-based clinical question answering,” J. Biomed. Inform., vol. 126, p. 104171, 2026. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/41610815/
4. M. K. Smith, C. Welty, and D. L. McGuinness, “OWL Web Ontology Language Guide (Wine Ontology Example),” World Wide Web Consortium (W3C), W3C Recommendation, 2004. [Online]. Available: https://www.w3.org/TR/owl-guide/
5. UC Davis Library, “Wine Ontology Project,” GitHub repository, 2016. [Online]. Available: https://github.com/UCDavisLibrary/wine-ontology
6. CheckSem, “The Wine Cloud Ontology,” Online ontology resource, 2023. [Online]. Available: https://ontology.winecloud.checksem.fr/
7. Libelium, “Smart Wine: IoT Technology Allows Predictive Control of Vineyard Management,” Libelium Case Studies, 2025. [Online]. Available: https://www.libelium.com/libeliumworld/successstories/smart-wine-libeliums-iot-technology-allows-predictive-control-ofvineyard-management/