Agentic AI Reference Architecture

Knowledge & Data · Software component

Multi-Signal Entity Resolver

Software componentKnowledge & DataKnowledge & Dataarc:MultiSignalEntityResolver

An entity linker that unifies records across source systems into canonical entities by combining name fuzzy and embedding similarity, contact overlap, known parent-subsidiary links and transaction-history patterns.

Responsibility. Resolves cross-system records of the same entity to one canonical identifier.

Also known as: Entity resolution, Entity unification

Variant of Entity Linker abstract

When to choose. Choose when the same real-world entity carries different identifiers across several source systems and string similarity alone is insufficient to unify them.

invokesspecializessends data toreceives data fromwritesis target of alternativeToText Embedding Service: invokesText Embedding ServiceEntity Linker: specializesEntity LinkerKnowledge Graph Loader: sends data toKnowledge Graph LoaderSource Record Extractor: receives data fromSource Record ExtractorEntity Reference Catalog: writesEntity Reference CatalogFuzzy-Match Entity Linker: is target of alternativeToFuzzy-Match Entity Linker
Direct neighbourhood (hover for relationship types)

Relationships

invokes dependency

writes dependency

receives data from dynamic

sends data to dynamic

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
Multi-signal matchingEmbedding-similarity candidate matching pending validation
Quality attributes
Compatibility (ISO/IEC 25010)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Fragmented entity views across legacy systemsIncorrect entity links polluting graph reasoning

Sources

  1. Ch5.8: T. Nguyen, "Semantic Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.8. ISBN: 9798244538229.