Resolve: Building Shipment-Centric Subgraphs

Extraction produces structured entities, but they're still disconnected fragments. The resolution layer links them together into coherent, shipment-centric subgraphs, complete operational pictures assembled automatically from fragmented communications.

How Resolution Works

The core challenge: given a set of identifiers extracted from a new email or document, determine which Shipment they belong to or whether a new Shipment should be created.

Our proprietary matching algorithm distinguishes between identifiers that define a shipment (like a House Bill of Lading) and identifiers that merely reference one (like an invoice number). This ensures high-precision matching while still capturing the full context around each shipment.

Multi-Shipment Detection

A single email often contains information about multiple shipments. The system detects these multi-order scenarios automatically and resolves each order group independently:

The Resolved Shipment

A single Shipment in the graph may aggregate context from 30+ emails, 15+ documents, and dozens of entities, all assembled automatically through intelligent matching. This is what makes Tally’s LCG architecture dramatically more valuable than a document store or flat database.

Once resolved, every extracted entity is linked to its shipment, building a complete operational picture:

Tally handles duplicate detection and merging (automatically combining shipment fragments that turn out to be the same movement) and party resolution (recognizing that "Maersk Line", "Maersk A/S", and "MAEU" refer to the same organization).