> ## Documentation Index > Fetch the complete documentation index at: https://docs.rkat.ai/llms.txt > Use this file to discover all available pages before exploring further. # Concepts overview > Follow a piece of evidence from its source to the graph, current answers, and derived pages. Meerkat Recall connects claims to the evidence that supports them. It keeps the original source, the extracted interpretation, and the current answer as separate records so that a reader can ask both **what do we know?** and **why do we believe it?** Consider a synthetic project note: "Mara joined Northstar Labs in March 2026." That sentence can support an employment relationship and a dated event. It does not, by itself, prove that Mara still works there today. ## From evidence to an answer ```mermaid theme={null} flowchart TD S["Source: where the note came from"] --> D["Document and immutable revision"] D --> N["Document nodes: structure and retrieval"] N --> A["Candidate extraction artifacts"] A --> C["Validate and commit"] C --> E["Assertions: claims with evidence spans"] C --> G["Entities, relationships, attributes, events"] E --> T["Truth maintenance"] G --> T P["Predicate vocabulary and semantics"] --> T T --> V["Truth slots: current values and uncertainty"] G --> W["Derived knowledge views and wiki"] V --> W ``` The diagram shows the graph-ingestion path. A source can also stop after metadata processing or document retrieval. Background work is asynchronous: accepting an ingest request does not mean its graph or wiki page is ready. ## What each record means | Concept | In the project-note example | Question it answers | | - | - | - | | [Source and document](/recall/concepts/documents) | The note, its origin, and an immutable rendered revision | Where did the evidence come from? | | [Assertion](/recall/concepts/assertions) | The extracted claim that Mara works at Northstar Labs, with a span into that revision | What did this source say? | | [Entity](/recall/concepts/entities) | Mara and Northstar Labs, each with a stable record ID | Which people or things are involved? | | [Relationship or attribute](/recall/concepts/relationships) | `Mara works_at Northstar Labs`; a separate literal-valued claim such as a role | What claim connects these records? | | [Event](/recall/concepts/events) | Mara joining in March, with month-level time precision | What happened, and when? | | [Predicate](/recall/concepts/predicates) | The meaning of `works_at`, its aliases, and whether multiple employers can coexist | How should this kind of claim behave? | | [Truth slot](/recall/concepts/truth-maintenance) | The supported current employment value or competing values | What answer should a reader use now? | | [Living Wiki](/recall/architecture/living-wiki) | A derived article citing the supported graph and source evidence | How can a person read the knowledge coherently? | Extraction is interpretive. The table illustrates possible records, rather than promising an exact number of rows or identical model output on every run. ## Identity, evidence, and truth are different decisions Three questions arise when another note says "Mara now works at Cedar Works": 1. **Identity:** is this the same Mara? Entity resolution uses names, identity keys, type compatibility, and, when configured, disambiguation. 2. **Vocabulary:** does "works at" mean the canonical `works_at` predicate? Predicate registration and alias governance answer that question. 3. **Truth:** did Mara change jobs, hold two roles, or appear in an ambiguous source? Truth maintenance evaluates the competing claim values and their configured semantics. A high extraction confidence addresses what the source says. It does not settle identity or prove that the statement remains true. ## Isolation and visibility Records belong to a [space](/recall/concepts/spaces). Within that space, [security envelopes](/recall/concepts/security) determine which records a principal can read or modify. Truth maintenance and knowledge views also preserve security boundaries: evidence from a more restricted envelope cannot silently become a less restricted answer. A missing search result can therefore mean that a record is unauthorized, not yet processed, excluded by a status filter, or absent. Inspect the relevant status and use the same principal and space when diagnosing it. ## Choose your next page Start with sources, revisions, and the processing depth you need. Choose entity identities, predicates, and claim shapes. Follow evidence, conflicts, validity, and staleness. Understand spaces, clearances, subjects, and derived reads. For a runnable starting point, use the [quickstart](/recall/quickstart). For exact request bodies, use the [HTTP API](/recall/api/overview) or [MCP tools](/recall/mcp/tools). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.