@base <https://cloud.google.com/blog/products/data-analytics/introducing-the-google-cloud-knowledge-catalog> .
@prefix schema: <https://schema.org/> .
@prefix owl: <https://www.w3.org/2002/07/owl#> .

<#article> a schema:Article ;
  schema:headline "Introducing the Google Cloud Knowledge Catalog"@en ;
  schema:name "Introducing the Google Cloud Knowledge Catalog"@en ;
  schema:datePublished "2026-04-22" ;
  schema:inLanguage "en" ;
  schema:url <https://cloud.google.com/blog/products/data-analytics/introducing-the-google-cloud-knowledge-catalog> ;
  schema:publisher <#google-cloud-blog> ;
  schema:author <#chai-pydimukkala>, <#sam-mcveety> ;
  schema:about
    <#google-cloud-knowledge-catalog>,
    <#dataplex-evolution>,
    <#universal-context-engine>,
    <#aggregation-pillar>,
    <#enrichment-pillar>,
    <#search-pillar>,
    <#broad-metadata-aggregation>,
    <#enterprise-connectivity>,
    <#lookml-agent>,
    <#bigquery-measures>,
    <#data-products>,
    <#smart-storage>,
    <#deep-multimodal-metadata-extraction>,
    <#automated-context-curation>,
    <#verified-queries>,
    <#high-precision-semantic-search>,
    <#access-control-aware-search>,
    <#context-evaluation>,
    <#deep-research-agent> ;
  schema:articleSection
    "Aggregation: Unifying context across your data estate"@en,
    "Enrichment: Generating meaning through continuous learning"@en,
    "Search: Unleashing agents with high-precision, secure retrieval"@en ;
  schema:abstract """The post introduces Google Cloud Knowledge Catalog as Dataplex's evolution into a dynamic enterprise context engine for AI agents, built around aggregation, enrichment, and search."""@en ;
  schema:articleBody """Google Cloud introduces Knowledge Catalog as a universal context engine designed to give AI agents trusted business semantics, relationships, and governed retrieval across enterprise data estates. The post argues that traditional catalogs focus too narrowly on technical structures and leave agents without the context needed to avoid hallucinations, latency, and stale insights. The new product strategy is organized around three pillars: aggregation of metadata and semantic assets across Google and partner systems, continuous enrichment of structured and unstructured data with business meaning, and secure high-precision search for agent retrieval. The article also ties the catalog to Dataplex, BigQuery measures, LookML, Smart Storage, verified SQL patterns, and Gemini Enterprise's Deep Research Agent."""@en ;
  schema:hasPart
    <#part-problem>,
    <#part-aggregation>,
    <#part-enrichment>,
    <#part-search>,
    <#part-agent-example> ;
  schema:mentions
    <#defined-terms>,
    <#argument-howto>,
    <#faq-1>, <#faq-2>, <#faq-3>, <#faq-4>, <#faq-5>,
    <#faq-6>, <#faq-7>, <#faq-8>, <#faq-9>, <#faq-10>,
    <#google-cloud>,
    <#dataplex>,
    <#bigquery>,
    <#looker>,
    <#gemini-enterprise>,
    <#bloomberg-media> .

<#google-cloud-blog> a schema:Blog ;
  schema:name "Google Cloud Blog"@en ;
  schema:url <https://cloud.google.com/blog/> ;
  schema:publisher <#google-cloud> .

<#google-cloud> a schema:Organization ;
  schema:name "Google Cloud"@en ;
  schema:url <https://cloud.google.com/> .

<#chai-pydimukkala> a schema:Person ;
  schema:name "Chai Pydimukkala"@en ;
  schema:jobTitle "Product Lead, Google Cloud"@en ;
  schema:affiliation <#google-cloud> .

<#sam-mcveety> a schema:Person ;
  schema:name "Sam McVeety"@en ;
  schema:jobTitle "Tech Lead, Google Cloud"@en ;
  schema:affiliation <#google-cloud> .

<#dataplex> a schema:SoftwareApplication, schema:Product ;
  schema:name "Dataplex"@en ;
  schema:url <https://cloud.google.com/dataplex> ;
  schema:brand <#google-cloud> .

<#bigquery> a schema:SoftwareApplication, schema:Product ;
  schema:name "BigQuery"@en ;
  schema:url <https://cloud.google.com/bigquery> ;
  schema:brand <#google-cloud> .

<#looker> a schema:SoftwareApplication, schema:Product ;
  schema:name "Looker"@en ;
  schema:url <https://cloud.google.com/looker> ;
  schema:brand <#google-cloud> .

<#gemini-enterprise> a schema:SoftwareApplication, schema:Product ;
  schema:name "Gemini Enterprise"@en ;
  schema:url <https://cloud.google.com/gemini> ;
  schema:brand <#google-cloud> .

<#bloomberg-media> a schema:Organization ;
  schema:name "Bloomberg Media"@en ;
  schema:url <https://www.bloombergmedia.com/> .

<#google-cloud-knowledge-catalog> a schema:SoftwareApplication, schema:Product ;
  schema:name "Google Cloud Knowledge Catalog"@en ;
  schema:brand <#google-cloud> ;
  schema:applicationCategory "Enterprise metadata and context engine"@en ;
  schema:description """The post presents Knowledge Catalog as the universal context engine for enterprise AI agents, built to unify metadata, enrich meaning, and provide secure retrieval."""@en .

<#dataplex-evolution> a schema:DefinedTerm ;
  schema:name "Dataplex evolution"@en ;
  schema:description """The article's framing that Dataplex is being evolved into an always-on Knowledge Catalog rather than remaining a traditional catalog surface."""@en .

<#universal-context-engine> a schema:DefinedTerm ;
  schema:name "Universal context engine"@en ;
  schema:description """The paper's core positioning for Knowledge Catalog: a governed source of enterprise context that agents can use to reason accurately."""@en .

<#aggregation-pillar> a schema:DefinedTerm ;
  schema:name "Aggregation pillar"@en ;
  schema:description """The first pillar of the product strategy, focused on unifying context from Google systems, partner platforms, semantic models, and third-party catalogs."""@en .

<#enrichment-pillar> a schema:DefinedTerm ;
  schema:name "Enrichment pillar"@en ;
  schema:description """The second pillar, centered on continuously generating business meaning, relationships, and descriptions from structured and unstructured sources."""@en .

<#search-pillar> a schema:DefinedTerm ;
  schema:name "Search pillar"@en ;
  schema:description """The third pillar, focused on high-precision, access-aware retrieval that lets agents find the right context at low latency."""@en .

<#broad-metadata-aggregation> a schema:DefinedTerm ;
  schema:name "Broad metadata aggregation"@en ;
  schema:description """The GA capability that automatically harvests technical metadata from core Google systems and partner catalogs to eliminate metadata silos."""@en .

<#enterprise-connectivity> a schema:DefinedTerm ;
  schema:name "Enterprise connectivity"@en ;
  schema:description """The Preview capability that federates context across enterprise applications and operating systems such as SAP, Salesforce Data360, ServiceNow, Workday, and Palantir."""@en .

<#lookml-agent> a schema:DefinedTerm ;
  schema:name "LookML agent"@en ;
  schema:description """The new automation capability that reads strategy documents and generates business-ready semantics, then contributes them to the shared catalog."""@en .

<#bigquery-measures> a schema:DefinedTerm ;
  schema:name "BigQuery measures"@en ;
  schema:description """The Preview feature that embeds reusable business logic into the SQL engine and feeds that logic into the catalog's semantic foundation."""@en .

<#data-products> a schema:DefinedTerm ;
  schema:name "Data products"@en ;
  schema:description """The GA building blocks that package data assets with intent, SLAs, and governance constraints to ground production AI use cases."""@en .

<#smart-storage> a schema:DefinedTerm ;
  schema:name "Smart Storage and Object Context API"@en ;
  schema:description """The Preview Google Cloud Storage capability that tags, embeds, and enriches files as they land so unstructured content becomes instantly discoverable."""@en .

<#deep-multimodal-metadata-extraction> a schema:DefinedTerm ;
  schema:name "Deep multimodal metadata extraction"@en ;
  schema:description """The Preview capability that uses Gemini to identify business information and relationships inside complex unstructured collections."""@en .

<#automated-context-curation> a schema:DefinedTerm ;
  schema:name "Automated context curation"@en ;
  schema:description """The Preview feature that generates natural-language descriptions, glossaries, relationships, and verified SQL patterns for both humans and agents."""@en .

<#verified-queries> a schema:DefinedTerm ;
  schema:name "Verified queries and semantic guardrails"@en ;
  schema:description """The Preview safeguard layer that provides trusted SQL patterns and natural-language questions to reduce hallucinated joins and guessed logic."""@en .

<#high-precision-semantic-search> a schema:DefinedTerm ;
  schema:name "High-precision semantic search"@en ;
  schema:description """The GA retrieval layer that uses hybrid search, query rewriting, and machine learning to rank and return relevant context for agents in real time."""@en .

<#access-control-aware-search> a schema:DefinedTerm ;
  schema:name "Access control-aware search"@en ;
  schema:description """The requirement that search respects source-system metadata permissions so agents only retrieve context they are authorized to see."""@en .

<#context-evaluation> a schema:DefinedTerm ;
  schema:name "Measurable context evaluation"@en ;
  schema:description """The capability that turns context construction into an engineering discipline by quantitatively evaluating retrieval relevance and quality."""@en .

<#deep-research-agent> a schema:DefinedTerm ;
  schema:name "Deep Research Agent"@en ;
  schema:description """The Gemini Enterprise agent example the post says is natively powered by Knowledge Catalog to synthesize live business data, internal documents, and web research."""@en .

<#defined-terms> a schema:DefinedTermSet ;
  schema:name "Defined terms for Introducing the Google Cloud Knowledge Catalog"@en ;
  schema:hasPart
    <#google-cloud-knowledge-catalog>,
    <#dataplex-evolution>,
    <#universal-context-engine>,
    <#aggregation-pillar>,
    <#enrichment-pillar>,
    <#search-pillar>,
    <#broad-metadata-aggregation>,
    <#enterprise-connectivity>,
    <#lookml-agent>,
    <#bigquery-measures>,
    <#data-products>,
    <#smart-storage>,
    <#deep-multimodal-metadata-extraction>,
    <#automated-context-curation>,
    <#verified-queries>,
    <#high-precision-semantic-search>,
    <#access-control-aware-search>,
    <#context-evaluation>,
    <#deep-research-agent> ;
  schema:isPartOf <#article> .

<#part-problem> a schema:WebPageElement ;
  schema:name "Why traditional catalogs are not enough"@en ;
  schema:position 1 ;
  schema:about <#universal-context-engine> ;
  schema:text """The article argues that traditional catalogs focus on table structures for technical users and leave AI agents without the semantics and relationships needed for reliable reasoning."""@en .

<#part-aggregation> a schema:WebPageElement ;
  schema:name "Aggregation"@en ;
  schema:position 2 ;
  schema:about <#aggregation-pillar>, <#broad-metadata-aggregation>, <#enterprise-connectivity>, <#lookml-agent>, <#bigquery-measures>, <#data-products> ;
  schema:text """The first pillar unifies metadata, semantic models, measures, and data products across Google systems, partner systems, and third-party catalogs into a governed source of truth."""@en .

<#part-enrichment> a schema:WebPageElement ;
  schema:name "Enrichment"@en ;
  schema:position 3 ;
  schema:about <#enrichment-pillar>, <#smart-storage>, <#deep-multimodal-metadata-extraction>, <#automated-context-curation>, <#verified-queries> ;
  schema:text """The second pillar continuously generates business meaning from schemas, logs, semantic models, and unstructured content, while adding guardrails such as verified queries."""@en .

<#part-search> a schema:WebPageElement ;
  schema:name "Search"@en ;
  schema:position 4 ;
  schema:about <#search-pillar>, <#high-precision-semantic-search>, <#access-control-aware-search>, <#context-evaluation> ;
  schema:text """The third pillar delivers low-latency, permission-aware search and measurable evaluation so agents can retrieve relevant context securely and consistently."""@en .

<#part-agent-example> a schema:WebPageElement ;
  schema:name "Deep Research Agent example"@en ;
  schema:position 5 ;
  schema:about <#deep-research-agent>, <#gemini-enterprise> ;
  schema:text """The article uses Gemini Enterprise's Deep Research Agent as the flagship example of what reliable agent deployment looks like once context, retrieval, and guardrails are in place."""@en .

<#argument-howto> a schema:HowTo ;
  schema:name "How the article builds the Knowledge Catalog argument"@en ;
  schema:about <#google-cloud-knowledge-catalog>, <#deep-research-agent> ;
  schema:isPartOf <#article> ;
  schema:step <#step-1>, <#step-2>, <#step-3>, <#step-4> ;
  schema:description """The post moves from the limits of traditional catalogs, to the three-pillar architecture, to concrete capabilities, and finally to an applied agent example."""@en .

<#step-1> a schema:HowToStep ;
  schema:name "Define the context problem"@en ;
  schema:position 1 ;
  schema:text "The article starts by arguing that agents fail when they only see raw technical metadata and lack business semantics and relationships."@en ;
  schema:isPartOf <#argument-howto> .

<#step-2> a schema:HowToStep ;
  schema:name "Introduce the three-pillar architecture"@en ;
  schema:position 2 ;
  schema:text "Knowledge Catalog is framed around aggregation, enrichment, and search as the architectural foundation for trusted enterprise context."@en ;
  schema:isPartOf <#argument-howto> .

<#step-3> a schema:HowToStep ;
  schema:name "Attach concrete capabilities and integrations"@en ;
  schema:position 3 ;
  schema:text "The post maps the architecture to capabilities like BigQuery measures, LookML agent, Smart Storage, verified queries, and partner-system federation."@en ;
  schema:isPartOf <#argument-howto> .

<#step-4> a schema:HowToStep ;
  schema:name "Show the agent outcome"@en ;
  schema:position 4 ;
  schema:text "The conclusion is that once grounded context and secure retrieval exist, agents like Deep Research can answer complex enterprise questions with higher accuracy and citations."@en ;
  schema:isPartOf <#argument-howto> .

<#faq-1> a schema:Question ;
  schema:name "What problem is Knowledge Catalog trying to solve?"@en ;
  schema:text "What problem is Knowledge Catalog trying to solve?"@en ;
  schema:acceptedAnswer <#faq-1-answer> ;
  schema:isPartOf <#article> .
<#faq-1-answer> a schema:Answer ;
  schema:text "It is meant to solve the lack of trusted business context and relationships that causes AI agents to hallucinate, respond slowly, or use stale insights."@en ;
  schema:isPartOf <#article> .

<#faq-2> a schema:Question ;
  schema:name "How is Knowledge Catalog positioned relative to Dataplex?"@en ;
  schema:text "How is Knowledge Catalog positioned relative to Dataplex?"@en ;
  schema:acceptedAnswer <#faq-2-answer> ;
  schema:isPartOf <#article> .
<#faq-2-answer> a schema:Answer ;
  schema:text "The post says Google Cloud is evolving Dataplex into an always-on Knowledge Catalog that acts as a universal enterprise context engine."@en ;
  schema:isPartOf <#article> .

<#faq-3> a schema:Question ;
  schema:name "What are the three foundational pillars?"@en ;
  schema:text "What are the three foundational pillars?"@en ;
  schema:acceptedAnswer <#faq-3-answer> ;
  schema:isPartOf <#article> .
<#faq-3-answer> a schema:Answer ;
  schema:text "The three pillars are aggregation, enrichment, and search."@en ;
  schema:isPartOf <#article> .

<#faq-4> a schema:Question ;
  schema:name "What does aggregation include?"@en ;
  schema:text "What does aggregation include?"@en ;
  schema:acceptedAnswer <#faq-4-answer> ;
  schema:isPartOf <#article> .
<#faq-4-answer> a schema:Answer ;
  schema:text "Aggregation spans native Google metadata, partner platforms, semantic models like LookML, BigQuery measures, and third-party catalogs such as Atlan, Collibra, and Datahub."@en ;
  schema:isPartOf <#article> .

<#faq-5> a schema:Question ;
  schema:name "What does enrichment add beyond a normal catalog?"@en ;
  schema:text "What does enrichment add beyond a normal catalog?"@en ;
  schema:acceptedAnswer <#faq-5-answer> ;
  schema:isPartOf <#article> .
<#faq-5-answer> a schema:Answer ;
  schema:text "It continuously mines schemas, logs, semantic models, and unstructured content to generate descriptions, relationships, embeddings, glossary terms, and verified patterns."@en ;
  schema:isPartOf <#article> .

<#faq-6> a schema:Question ;
  schema:name "Why is search treated as the new query path?"@en ;
  schema:text "Why is search treated as the new query path?"@en ;
  schema:acceptedAnswer <#faq-6-answer> ;
  schema:isPartOf <#article> .
<#faq-6-answer> a schema:Answer ;
  schema:text "Because autonomous agents iterate rapidly and need low-latency retrieval of the right context, so search becomes the main path by which they find what to reason over."@en ;
  schema:isPartOf <#article> .

<#faq-7> a schema:Question ;
  schema:name "How does the post say hallucinations are reduced?"@en ;
  schema:text "How does the post say hallucinations are reduced?"@en ;
  schema:acceptedAnswer <#faq-7-answer> ;
  schema:isPartOf <#article> .
<#faq-7-answer> a schema:Answer ;
  schema:text "By grounding agents in unified context, access-aware retrieval, verified SQL patterns, and semantic guardrails rather than forcing them to infer logic from sparse metadata."@en ;
  schema:isPartOf <#article> .

<#faq-8> a schema:Question ;
  schema:name "What role do data products play?"@en ;
  schema:text "What role do data products play?"@en ;
  schema:acceptedAnswer <#faq-8-answer> ;
  schema:isPartOf <#article> .
<#faq-8-answer> a schema:Answer ;
  schema:text "The article says data products package assets with intent, SLAs, and governance constraints so they can reliably ground production AI use cases."@en ;
  schema:isPartOf <#article> .

<#faq-9> a schema:Question ;
  schema:name "Why is measurable context evaluation important?"@en ;
  schema:text "Why is measurable context evaluation important?"@en ;
  schema:acceptedAnswer <#faq-9-answer> ;
  schema:isPartOf <#article> .
<#faq-9-answer> a schema:Answer ;
  schema:text "It turns context construction into a quantifiable engineering process, letting teams test and improve relevance and quality instead of guessing."@en ;
  schema:isPartOf <#article> .

<#faq-10> a schema:Question ;
  schema:name "What is the flagship agent example in the article?"@en ;
  schema:text "What is the flagship agent example in the article?"@en ;
  schema:acceptedAnswer <#faq-10-answer> ;
  schema:isPartOf <#article> .
<#faq-10-answer> a schema:Answer ;
  schema:text "The flagship example is Gemini Enterprise's Deep Research Agent, which the post says is natively powered by Knowledge Catalog."@en ;
  schema:isPartOf <#article> .