Triple

T16534328
Position Surface form Disambiguated ID Type / Status
Subject Bernardston, Massachusetts E401648 entity
Predicate adjacentTo P224 FINISHED
Object Vernon, Vermont NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Vernon, Vermont | Statement: [Bernardston, Massachusetts, adjacentTo, Vernon, Vermont]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vernon, Vermont
Context triple: [Bernardston, Massachusetts, adjacentTo, Vernon, Vermont]
  • A. Vernon, Vermont chosen
    Vernon, Vermont is a small rural town in southeastern Vermont known for its scenic Connecticut River setting and former Vermont Yankee Nuclear Power Station.
  • B. Fairfield, Vermont
    Fairfield, Vermont is a small rural town in Franklin County best known as the birthplace of the 21st U.S. president, Chester A. Arthur.
  • C. Marlboro, Vermont
    Marlboro, Vermont is a small rural town in southern Vermont known for its scenic Green Mountain setting and its former Marlboro College campus.
  • D. Elmore, Vermont
    Elmore, Vermont is a small rural town in northern Vermont known for its scenic Lake Elmore and Elmore State Park.
  • E. Vergennes, Vermont
    Vergennes, Vermont is the smallest city by area in the United States and one of Vermont’s oldest chartered cities, known for its historic downtown and location along Otter Creek.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32eda42548190be61efb25a44a554 completed April 18, 2026, 7:12 a.m.
Created at: April 10, 2026, 5:15 a.m.