Schmidt, Wilma JohannaWilma JohannaSchmidtGrangel-González, IrlánIrlánGrangel-GonzálezHuschle, TobiasTobiasHuschleWagner, LenaLenaWagnerKharlamov, EvgenyEvgenyKharlamovPaschke, AdrianAdrianPaschke2025-11-112025-11-112026https://publica.fraunhofer.de/handle/publica/49909510.1007/978-3-031-99554-5_252-s2.0-105020237620In large manufacturing companies, such as Bosch, which operate thousands of production lines with up to dozens of items of production equipment, even simple inventory questions such as of quantity or location of a particular machine type require non-trivial solutions. Addressing these questions requires to integrate multiple heterogeneous data sets which is time consuming and demands domain as well as knowledge experts. Knowledge graphs (KGs) are practical for consolidating inventory data by bringing it into the same format and linking inventory items. The KG creation and maintenance, yet, pose challenges as mappings are needed to connect data sets and ontologies. In our work, we address this by exploring LLM-supported and context-enhanced YARRRML mapping generation. We further evaluate ontology reduction methods as we face large ontologies in the manufacturing domain and token limitations in LLM prompts. Our work provides valuable support when creating YARRRML manufacturing mappings as well as supporting data and schema updates. We evaluate our approach quantitatively against manually created reference mappings and qualitatively with expert feedback. This poster accompanies our in-use track paper at ESWC’25 [3].enfalseconference paper