EntityWeaver: Visual Exploration and Curation of Named-Entity Relationships in Document Collections

2026-09-29

AI Summary

This study addresses the challenges of quantifying uncertainty and bridging the gap between distant and close reading when exploring named entity relationships across document collections. We propose an uncertainty-aware interactive visualization system that pioneers the integration of link uncertainty into graph representations, employing scientific visualization transfer functions to control edge mapping. By combining multi-stage filtering queries, minimap navigation, and coordinated text views, the system establishes a unified workflow for large-scale pattern discovery and immediate source-text verification. Evaluations by domain experts demonstrate that the system effectively supports the identification of strong and weak associations, ambiguity resolution, and error correction, thereby significantly enhancing document curation efficiency.

Abstract

We present an interactive visualization system for exploring named entities and their relationships across document collections, with a strong focus on handling uncertainty and supporting both distant and close reading. The system is built around a graph that links documents, entity mentions, and entities. Uncertainty from mention-to-entity linking is included directly in this graph, so users can see where connections are strong, weak, or ambiguous. A transfer-function control, inspired by approaches in scientific visualization, allows users to adjust how this uncertainty is displayed, making it easy to tune the visualization for different datasets and research questions. The system also provides direct access to the full source texts in a coordinated view, enabling quick context checks, resolving ambiguous cases, and correcting digitization errors. Exploration is further supported through a multi-stage filter query builder, mini-map navigation for large graphs, and export options for downstream analysis. By combining uncertainty-aware graph visualization with direct interaction in the source texts, the system provides a unified workflow that supports both large-scale pattern discovery and curation of named-entity-based document collections. The design choices were supported by the domain experts, who were also involved in the initial system evaluation.

Problem

• named-entity relationships
• document collections
• uncertainty
• visual exploration
• entity linking

Innovation

• Named-Entity Relationships
• Uncertainty-Aware Visualization
• Interactive Graph Exploration
• Transfer-Function Control
• Coordinated Views