Knowledge Base

Entity Linking

Linking mentions to knowledge base entities.

0 datasets0 resultsView full task mapping →

Entity linking maps mentions of entities in text to their corresponding entries in a knowledge base (Wikipedia, Wikidata). BLINK and GENRE established neural entity linking, while LLMs now enable zero-shot entity resolution that handles ambiguity and out-of-knowledge-base entities with conversational context.

History

2011

TAC-KBP shared tasks establish entity linking evaluation methodology

2015

Neural entity linking with entity embeddings begins to outperform feature-based methods

2019

BLINK (Facebook) uses bi-encoder architecture for scalable entity retrieval and linking

2020

GENRE (Facebook) generates entity names autoregressively — constrained decoding over entity trie

2021

De Cao et al. show autoregressive entity linking handles ambiguous and out-of-KB entities

2022

EntQA frames entity linking as question answering for better context understanding

2023

ReFinED (Amazon) provides an efficient, production-grade entity linking system

2024

LLM-based entity linking — GPT-4/Claude resolve entity mentions with conversational context

2025

Multimodal entity linking handles entities mentioned in images, tables, and video alongside text

How Entity Linking Works

1Mention DetectionEntity mentions are identif…2Candidate GenerationFor each mention3Context EncodingThe mention and its surroun…4Entity RankingCandidates are ranked by si…5NIL DetectionIf no candidate exceeds a c…Entity Linking Pipeline
1

Mention Detection

Entity mentions are identified in the text — proper nouns, acronyms, and referential expressions that could correspond to KB entities.

2

Candidate Generation

For each mention, a set of candidate KB entities is retrieved — using alias tables, TF-IDF, or dense retrieval (bi-encoder).

3

Context Encoding

The mention and its surrounding context are encoded into a dense vector that captures the meaning in this specific usage.

4

Entity Ranking

Candidates are ranked by similarity between the context encoding and entity representations (descriptions, type information).

5

NIL Detection

If no candidate exceeds a confidence threshold, the mention is classified as NIL — referring to an entity not in the knowledge base.

Current Landscape

Entity linking in 2025 is a mature NLP component used in search engines, knowledge graphs, and information extraction pipelines. The bi-encoder + cross-encoder paradigm (BLINK) provides the speed-accuracy tradeoff for production, while autoregressive methods (GENRE) handle harder cases. LLMs are increasingly used for entity linking in applications where accuracy on ambiguous mentions matters more than throughput. The field is shifting toward more challenging settings: low-resource languages, domain-specific KBs (biomedical, legal), and multimodal entity resolution.

Key Challenges

Ambiguity — 'Washington' could be a person, state, city, university, or sports team

Long-tail entities — rare entities have few mentions in training data and sparse KB descriptions

Cross-lingual linking — mentions in one language must link to entities in a multilingual KB

Knowledge base evolution — new entities appear constantly; the KB is never complete

NIL clustering — grouping mentions of the same novel entity that isn't in the KB

Quick Recommendations

Production entity linking

ReFinED (Amazon)

Fast, accurate, and maintained — best production-ready system

Research baseline

BLINK (bi-encoder + cross-encoder)

Well-documented, reproducible, and widely compared against

Zero-shot / novel entities

GPT-4 / Claude with KB context

LLMs handle ambiguity and out-of-KB entities through reasoning

Multilingual linking

mGENRE

Multilingual autoregressive entity linking across 100+ languages

What's Next

The frontier is dynamic entity linking — handling knowledge bases that change in real-time (news events, new products, emerging entities). Expect integration with retrieval-augmented generation (RAG) systems, where entity linking grounds LLM outputs in verified knowledge, and multimodal entity linking that resolves entities across text, images, and video.

Benchmarks & SOTA

No datasets indexed for this task yet.

Contribute on GitHub

Related Tasks

Something wrong or missing?

Help keep Entity Linking benchmarks accurate. Report outdated results, missing benchmarks, or errors.

0/2000