Skip to main content

Overview

During document ingestion, the AI classifies documents and extracts entities. When confidence is low or conflicts arise, items are queued for manual review. The conflict resolution interface lets administrators review these cases and provide corrections. Navigate to Admin > Graph > Conflict Resolution.

Classification threshold

Each data source has a classification review threshold, set on the connector setup form next to Classification Max Pages. The default is 0.8. A document whose top score is below that value is queued here. Scores at or above it continue ingestion. On this page, pick a data source and edit its threshold. Apply shows how many pending items will continue ingestion, how many will be skipped because their top type is None, how many have no usable score and stay queued, how many stay because they are still under the cutoff, and how many already-classified files sit under the new cutoff. Confirming rechecks stored scores only. It does not call the model again. Files that already classified stay ingested. Saving the threshold on the connector form does not recheck the queue. An unscored review, or one whose scores are all zero, stays in the queue for a person to resolve.

Classification Reviews

When the AI is uncertain about how to classify a document or which content type it belongs to, the document enters the review queue. For each review item, you can see:
  • Document preview — A text excerpt from the document
  • AI classification — The AI’s suggested classification with confidence score
  • Alternative classifications — Other possible classifications the AI considered
  • Resolution status — Pending, approved, or rejected

Resolving Classifications

  1. Review the document preview and AI suggestions
  2. Select the correct classification
  3. Submit your decision
Your corrections improve future AI accuracy by providing feedback to the classification model.

Entity Match Reviews

When the matching system identifies potential duplicate entities but isn’t confident enough to auto-merge them, they appear in the match review queue. Each match review shows:
  • Entity data — The entity in question with its properties
  • Candidate matches — Potential duplicate entities ranked by match score
  • Match score — Confidence level for each candidate

Review Actions

Status Indicators

Match reviews display color-coded status:
  • Pending (orange) — Awaiting review
  • Approved (green) — Merged with a candidate
  • Merged (blue) — Successfully combined
  • Rejected (red) — Confirmed as distinct entities
Review conflicts regularly, especially during initial ingestion. Early corrections significantly improve the AI’s accuracy for subsequent document processing.