Ontology Alignment Evaluation Initiative - OAEI-2025 Campaign

GeneralRelation

General description

The GeneralRelation track evaluates ontology matching systems on their ability to detect general semantic relations beyond simple equivalence. This better reflects real-world ontology alignment scenarios, where ontologies may differ in structure, granularity, and classification perspective.

Five mutually disjoint relation types are included:

This track addresses the need for alignment approaches capable of capturing nuanced relationships, enabling richer semantic integration for tasks such as knowledge graph merging, master data integration, and semantic search.

Datasets

The benchmark dataset suite is publicly available via Zenodo:

The datasets come from three major sources: Product Classification Standards (ETIM, eClass, UNSPSC, GPC), STROMA/TaSeR Test Cases, and Modified OAEI Testcases. They vary in size, structure, and semantic complexity, and all reference alignments are annotated with explicit relation types.

Source Dataset # Source Classes # Target Classes # Source Properties # Target Properties
Product Classification Standards GPC–UNSPSC 1,15130,707 8393 2551,37725017,738
GPC–UNSPSC+ 5,34230,707 8393 3813,306129323,600
STROMA/TaSeR Test Cases g1–web 7281,132 00 1752629
g2–diseases 1,1095,146 00 3161127
g3–text 335260 00 70267425
g5–groceries 60335 00 2911314
g7–literature 41155 00 125218
Modified OAEI Testcases Anatomy* 2,4412,773 32 676671600

Data Features

Related Links

Contact

For inquiries or to request evaluation support, please contact the track organizers:
Xianhao Liu (xliu@stibosystems.com),
Sven Hertling (sven.hertling@uni-mannheim.de),
Michael R. Hansen (mire@dtu.com)