# November 28: Support for entity resolution, agentic GraphRAG, user-scoped knowledge graphs ### New Features * 💡 Graphlit now supports **LLM-based entity resolution** via the `resolveEntities` mutation. You can provide a list of JSON-LD entities to the model, and it will return a resolved list with fields merged or new entities split out, helping to deduplicate and consolidate your knowledge graph. * 💡 We have expanded our **agentic GraphRAG capabilities** by breaking out specific SDK calls for graph tools, allowing an agentic LLM to manipulate the knowledge graph directly rather than relying solely on graph strategy configuration. * Graphlit now supports **user-specific knowledge graphs**. For multi-tenant applications, each user can have their own isolated knowledge graph rather than sharing a project-wide graph. * We have added support for **on-demand entity enrichment**. You can now select entities and enrich them with external data sources like Diffbot, Crunchbase, or Parallel to fill in websites, addresses, funding information, and more. * Observable entities now expose their `feed` property to the API, and you can filter entities by feed using the updated observable filter. ### Bugs Fixed * GPLA-4748: Fixed entity validation errors when upserting Organization entities * GPLA-4743: Enrichment now correctly creates and assigns Founder relationships from JSON-LD * GPLA-4725: `graph` query now returns inter-entity edges that were being ignored * GPLA-4728: Deleting a CRM feed now recursively deletes entities sourced from it --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://changelog.graphlit.dev/november-2025/november-28-support-for-entity-resolution-agentic-graphrag-user-scoped-knowledge-graphs.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.