Agentic AI Reference Architecture

Knowledge & Data · Data store

Entity Reference Catalog

Data storeKnowledge & DataKnowledge & Dataarc:EntityReferenceCatalog

A reference knowledge base of canonical entity identifiers (e.g., encyclopedic IDs, ticker symbols) used to resolve entity mentions.

Responsibility. Supplies canonical identifiers for entity resolution.

Also known as: Reference Knowledge Base, Company Database, Brand-to-generic name mapping, Canonical entity identifier crosswalk

is read byis read byis written byis read byRetriever: is read byRetrieverEntity Linker: is read byEntity LinkerMulti-Signal Entity Resolver: is written byMulti-Signal Entity Reso…Knowledge-Base Entity Linker: is read byKnowledge-Base Entity Li…
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
Wikidata QIDsCompany ticker symbols

Sources

  1. 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.
  2. Ch3.2: T. Nguyen, "Compare Agent Performance Across Tasks and Datasets," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.2. ISBN: 9798244538229.
  3. 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.