Back to Arena
Ontotext GraphDB
by Ontotext / Graphwise (merged with Semantic Web Company, 2025)
System Card
OrganizationOntotext / Graphwise (merged with Semantic Web Company, 2025)
Released2000-01
Architecturegraph-rag / RDF triplestore with OWL2 inference
DetailsOntotext GraphDB (formerly OWLIM) is an enterprise RDF triplestore optimized for large-scale knowledge graph inference and linked data publishing. It supports full OWL2 RL/EL/QL reasoning, SPARQL 1.1, and connectors to Elasticsearch and Solr for hybrid search. In 2025, Ontotext merged with Semantic Web Company to form Graphwise, adding PoolParty taxonomy management.
Parameters—
Domainknowledge-graphrag-retrieval
Open SourcePartial
WebsiteVisit
RDFOWL2inferenceSPARQLlinked-data
Capability Profile
Benchmark Scores
6 of 14 benchmarksMulti-Turn Recall0/2
LoCoMo
no dataMemoryBank
no dataCross-Session Memory1/1
Multi-Hop QA2/3
Agent Task Memory0/1
AgentBench-Mem
no dataPersonalization0/1
PerLTQA
no dataFactuality / Grounding1/1
Sources:Ontotext GraphDB vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Ontotext GraphDB vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Ontotext GraphDB vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)Ontotext GraphDB vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Ontotext GraphDB vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Ontotext GraphDB vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)