Ontology-driven knowledge graph extraction from text
Details
- External ID
- 46032953
- Source
- HN
- Company
- —
- Product
- —
- Website domain
- —
- Launched
- Nov. 24, 2025
- Cohort
- —
- Upvotes
- 13
- Upvotes percentile
- 0.5796943231441049
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
TrustGraph now supports automatic knowledge graph construction guided by OWL ontologies. You provide an ontology (OWL/Turtle format or build one in the Workbench editor), point it at your documents, and it extracts entities and relationships that conform to your schema.The problem this solves: generic GraphRAG approaches extract whatever relationships an LLM thinks are relevant, which often misses domain-specific semantics. If you're working in healthcare, finance, or intelligence analysis, you likely already have ontologies (or can adapt standards like SOSA, FIBO, etc.) that define what matters. TrustGraph uses these to constrain extraction, so the resulting graph reflects your domain model rather than the LLM's interpretation.How it works: The ontology defines classes and properties. During extraction, the LLM is prompted to identify instances of those classes and relationships matching those properties. The output is validated against the schema before being written to the graph store.Built on Apache Pulsar for scalability, supports multiple graph backends (Memgraph, FalkorDB, others), and runs locally or in cloud. Apache 2.0 licensed.Repo: https://github.com/trustgraph-ai/trustgraphOntology RAG docs: https://docs.trustgraph.ai/guides/ontology-rag/Happy to answer questions about the extraction approach or architecture.
Enrichment
- Theme
- browser automation and scraping for AI
- Vertical
- Horizontal
- Function
- Data infrastructure
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- knowledge graph extraction from text
- Manually corrected
- False
Could you build this?
Partial The UI and standard LLM prompting for entity extraction can be vibe-coded, but robustly enforcing complex OWL schema constraints, validation, and semantic reasoning requires specialized knowledge engineering.
What it would actually take: The architecture requires an ontology parser (e.g., Apache Jena, rdflib), an LLM extraction pipeline using constrained decoding or grammar-guided generation, and an RDF triple store (such as Neo4j or Ontotext GraphDB). The hard technical problem is automated entity alignment, coreference resolution, and strict OWL-DL consistency checking against ontological axioms without hallucinating relations. This requires background in formal knowledge representation, Semantic Web standards (RDF/OWL/SHACL), and advanced graph data modeling.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 69 launches clear the similarity bar, closest 8 shown.
Attention rank: #29 of 70 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 26 days after the earliest competitor.
- TypeGraph · hn · 2026-02-24 · 5 upvotes · similarity 0.53
- genpark-graph-rag-entity-relationship-extractor-skill · github · 2026-09-28 · 7 upvotes · similarity 0.52
- jevgraph · github · 2026-09-20 · 19 upvotes · similarity 0.52
- ontology_modeling_framework · github · 2026-09-12 · 14 upvotes · similarity 0.51
- Kanon 2 Enricher · hn · 2026-03-03 · 10 upvotes · similarity 0.47
- What 180k words look like as a temporal knowledge graph (Oz series) · hn · 2026-07-26 · 22 upvotes · similarity 0.47
- ExtractBench, an open-source schema extraction benchmark · hn · 2026-08-11 · 6 upvotes · similarity 0.43
- BlitzGraph · hn · 2026-06-16 · 15 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a data infrastructure tool for Media & entertainment yet.