thunlp/OpenNRE

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4467 stars · 1049 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenNRE is an open-source Python toolkit for neural relation extraction, extracting relation triples between entities from plain text. It unifies supervised and distant supervision models, including CNN-based and pre-trained language model approaches, for knowledge graph construction.

Use cases

• extract relation triples from sentences
• build a knowledge graph from plain text
• train relation extraction models on custom datasets
• use pretrained relation extraction models in production
• run NLP research experiments on relation extraction benchmarks
• identify relationships between named entities in documents

When to choose

• you need relation extraction for knowledge graph construction
• you want a unified framework to compare NRE models
• you need pretrained models for entity-relation extraction
• you are an NLP researcher benchmarking relation extraction methods

When to avoid

• you need general-purpose NLP pipelines beyond relation extraction
• you want a maintained project with frequent updates
• you need production-grade entity extraction without training data
• your task is entity recognition rather than relation classification

Facets

library · maturity maintenance

nlp machine-learning deep-learning machine-learning artificial-intelligence python relation-extraction knowledge-graph information-extraction pretrained-models natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="thunlp/OpenNRE")