Triple

T2388843
Position Surface form Disambiguated ID Type / Status
Subject Southern Maine E48893 entity
Predicate contains P35 FINISHED
Object Westbrook, Maine E350746 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: Westbrook, Maine | Statement: [Southern Maine, contains, Westbrook, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Westbrook, Maine
Context triple: [Southern Maine, contains, Westbrook, Maine]
  • A. Westbrook, Maine chosen
    Westbrook, Maine is a small city in Cumberland County, just west of Portland, known for its historic mill industry and growing residential and commercial development.
  • B. Lovell, Maine
    Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
  • C. Winslow, Maine
    Winslow, Maine is a small town in Kennebec County known for its rural character, historic sites, and location along the Kennebec River in central Maine.
  • D. Blaine, Maine
    Blaine, Maine is a small rural town located in northeastern Maine near the Canadian border, within Aroostook County’s agricultural region.
  • 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_69c79c6a0fdc8190be37008d4f036e51 completed March 28, 2026, 9:16 a.m.
Created at: March 4, 2026, 7:57 p.m.