Relation Extraction & Knowledge Graph Construction
NER found the entities. Entity linking anchored them. Relation extraction finds the edges between them. A knowledge graph is the sum of nodes, edges, and their provenance. An analyst reads: "Tim Cook became CEO of Apple in 2011." Four facts: (Tim Cook, role, CEO). (Tim Cook, employer, Apple). (Tim Cook, startdate, 2011). (Apple, type, Organization). Relation Extraction (RE) turns free text into structured triples (subject, relation, object). Aggregate across a corpus and you have a knowledge graph. Aggregate and query and you have a reasoning substrate for RAG, analytics, or compliance audits. The 2026 problem: LLMs extract relations enthusiastically. Too enthusiastically. They hallucinate triples that the source text does not support. Without provenance, you cannot tell real triples from plausible fiction. The 2026 answer is AEVS-style anchor-and-verify pipelines. Text → triples → knowledge graph Triple form. (subjectentity, relationtype, objectentity). Relations come from a closed ontology (Wikidata properties, FIBO, UMLS) or an open set (OpenIE-style, anything goes). Three extraction approaches. Rule / pattern-based. Hearst patterns: "X such as Y" → (Y, isA, X). Plus hand-crafted regex. Brittle, precise, explainable. Supervised classifier. Given two entity mentions in a sentence, predict the relation from a fixed set. Trained on TACRED, ACE, KBP. Standard 2015–2022. Generative LLM. Prompt the model to emit triples. Works out of the box. Needs provenance, or hallucinates plausible-looking junk.…
Relation Extraction & Knowledge Graph Construction: NER found the entities. Entity linking anchored them. Relation extraction finds the edges between them. A…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.