Triple

T2388872
Position Surface form Disambiguated ID Type / Status
Subject Southern Maine E48893 entity
Predicate contains P35 FINISHED
Object Gray, Maine E445354 NE FINISHED

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: Gray, Maine | Statement: [Southern Maine, contains, Gray, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gray, Maine
Context triple: [Southern Maine, contains, Gray, Maine]
  • A. Gray, Maine chosen
    Gray, Maine is a small New England town in southern Maine known for its rural character, proximity to Portland, and the Maine Wildlife Park.
  • B. Warren, Maine
    Warren, Maine is a small town in Knox County known for its rural character and location along the St. George River in midcoast Maine.
  • C. Rockland, Maine
    Rockland, Maine is a coastal city in midcoast Maine known for its busy harbor, maritime industries, and role as a transportation and cultural hub for the region.
  • D. Greene, Maine
    Greene, Maine is a small rural town in Androscoggin County known for its quiet residential character and proximity to the Lewiston–Auburn area.
  • E. Porter, Maine
    Porter, Maine is a small rural town in Oxford County known for its scenic setting near the New Hampshire border and its traditional New England character.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc7dca9248190b634ae9e02f6899a completed March 7, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69c870539eb08190936adcfbab395654 completed March 29, 2026, 12:20 a.m.
Created at: March 4, 2026, 7:57 p.m.