Enterprise Knowledge Graph reconciles siloed enterprise data through an entity reconciliation API in BigQuery. The service is in Preview per the documentation.
What is Enterprise Knowledge Graph?
Enterprise Knowledge Graph organizes siloed information into organizational knowledge, which involves consolidating, standardizing, and reconciling data in an efficient and useful way.
Launch stage: The documentation marks the product as Preview. It is subject to the Pre-GA Offerings Terms in the General Service Terms section of the Service Specific Terms. Pre-GA products are available “as is” and might have limited support. You can process personal data for this product as outlined in the Cloud Data Processing Addendum, subject to the obligations and restrictions described in the agreement under which you access Google Cloud.
Core Features
- Entity Reconciliation API: A lightweight, AI-powered semantic clustering and deduplication service for tabular data
- Pretrained model: State-of-the-art quality pretrained model built with Google data
- Entity enrichment: Built-in enrichment, including geocoding
- Scale: Google-scale clustering and reconciliation handling a graph with a size up to billions of nodes and trillions of edges per the documentation
- Stable Machine ID (MID): A unique identifier for each entity cluster
- BigQuery integration: Native support for up to 10 BigQuery tables
- Google Knowledge Graph Search API: Search by keyword or look up entities with an ID, using standard schema.org types
Typical Use Cases
Consolidating customer data
Reconciling records from different systems in which the same person or organization is spelled differently.
Joining external datasets
Joining your own data with one or multiple third-party datasets through a common identifier.
Deduplicating tabular data
Semantic clustering instead of pure key matching when clean foreign keys are not available.
Entity lookup
Looking up entities by keyword or ID using the Google Knowledge Graph Search API.
Benefits
- Semantic matching: Reconciliation through fuzzy text, common relationships, entity types, and attributes rather than keys alone
- Stable identifier: The Stable Machine ID uniquely identifies entity clusters
- Direct BigQuery integration: Input and output live in BigQuery tables
- Pretrained model: No training of your own required
Integration with innFactory
As a certified Google Cloud partner, innFactory supports you with Enterprise Knowledge Graph: preparing the source BigQuery tables, mapping them to a common schema, and evaluating the reconciliation results. Keep the product’s Preview status in mind.
Contact us for a consultation on Enterprise Knowledge Graph.
Available Tiers & Options
Entity Reconciliation API
- Semantic clustering and deduplication for tabular data
- Pretrained model built with Google data
- Built-in entity enrichment, including geocoding
- Native support for up to 10 BigQuery tables
- Preview status under the Pre-GA Offerings Terms
- Input and output data live in BigQuery
Google Knowledge Graph Search API
- Search by keyword or look up entities with an ID
- Uses standard schema.org types
- A complementary search interface, not a replacement for reconciling your own data
Typical Use Cases
Technical Specifications
Frequently Asked Questions
What is Enterprise Knowledge Graph?
Enterprise Knowledge Graph organizes siloed information into organizational knowledge, which involves consolidating, standardizing, and reconciling data in an efficient and useful way. The service is in Preview per the documentation.
What does the Entity Reconciliation API do?
The Entity Reconciliation API is a lightweight, AI-powered semantic clustering and deduplication service for tabular data. It is a standalone API that wraps around the Google core entity resolution engine and helps customers reconcile and join their data together, or join their data with one or multiple third-party datasets.
How does the processing work technically?
The Entity Reconciliation API reads data from source BigQuery tables given a set of entity types and files mapped to a common schema. It then performs knowledge extraction to turn the relational input data into RDF triples, the Google entity reconciliation engine builds a graph to cluster entities into groups, and the linking result is written to customer-specified BigQuery tables as a new unique identifier column (MID).
What is the launch stage of the service?
The documentation marks Enterprise Knowledge Graph as Preview. The product is subject to the Pre-GA Offerings Terms in the General Service Terms section of the Service Specific Terms; pre-GA products are available "as is" and might have limited support.
What does Enterprise Knowledge Graph cost?
Google does not publish a dedicated pricing page for Enterprise Knowledge Graph. The official documentation is authoritative.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of Google Cloud (official documentation). This page does not represent an offer by Google Cloud.
