Knowledge & Data · Software component
Entity Linker
Software componentKnowledge & DataKnowledge & DataVariation point (abstract)arc:EntityLinker
An abstract software component that resolves entity mentions with varying surface forms to a single canonical entity identifier.
Responsibility. Resolves entity mentions to canonical identifiers.
Also known as: Entity Disambiguator, Entity Resolver, Entity Canonicalizer
Variants
| Variant | When to choose |
|---|---|
| Fuzzy-Match Entity Linker | Choose for lower-precision applications; matches by edit distance with manual review of uncertain mappings. |
| Knowledge-Base Entity Linker | Choose for high-precision requirements; resolves mentions to knowledge-base IDs via an entity linking service. |
| Multi-Signal Entity Resolver | Choose when the same real-world entity carries different identifiers across several source systems and string similarity alone is insufficient to unify them. |
Relationships
is invoked by dependency
- Hybrid Retriever abstract Ch1.7A
reads dependency
receives data from dynamic
sends data to dynamic
- Relation Extractor abstract Ch1.7A
Design guidance
- MUST resolve mentions to canonical identifiers before graph population, otherwise duplicate nodes break relationship queries.
- SHOULD key nodes on canonical IDs and store surface forms as aliases rather than using extracted text as identifiers.
Classification
- Patterns
- Entity linkingAlias storage on canonical node
- Quality attributes
- Security (ISO/IEC 25010 | NIST AI RMF: secure and resilient)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
- Risks mitigated
- Graph fragmentation from duplicate entity nodes
Sources
- Ch1.7A: T. Nguyen, "Relational Reasoning with Knowledge Graphs - The Fundamentals, Integration, and Extraction," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.7A. ISBN: 9798244538229.
- Ch1.7B: T. Nguyen, "Relational Reasoning with Knowledge Graphs - Hybrid RAG+KG Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.7B. ISBN: 9798244538229.