> For the complete documentation index, see [llms.txt](https://docs.tallygo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tallygo.ai/context-graph-overview/resolve-building-shipment-centric-subgraphs.md).
# 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).
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## 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://docs.tallygo.ai/context-graph-overview/resolve-building-shipment-centric-subgraphs.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.