Triple

T2388846
Position Surface form Disambiguated ID Type / Status
Subject Southern Maine E48893 entity
Predicate contains P35 FINISHED
Object York, Maine E364928 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: York, Maine | Statement: [Southern Maine, contains, York, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: York, Maine
Context triple: [Southern Maine, contains, York, Maine]
  • A. York, Maine chosen
    York, Maine is a historic coastal town in southern Maine known for its beaches, lighthouses, and status as one of the oldest European-settled communities in the United States.
  • B. Cambridge, Maine
    Cambridge, Maine is a small rural town in central Maine known for its quiet, forested landscape and location within Somerset County.
  • C. Manchester, Maine
    Manchester, Maine is a small town in central Maine known for its rural character and proximity to the state capital, Augusta.
  • D. Fairfield, Maine
    Fairfield, Maine is a small town in Somerset County known for its rural character, proximity to the Kennebec River, and role as part of the greater Waterville area in central Maine.
  • E. Winthrop, Maine
    Winthrop, Maine is a small New England town known for its lakes, outdoor recreation, and residential community west of Augusta.
  • 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_69c7b89011a88190b498264ff99e7984 completed March 28, 2026, 11:16 a.m.
Created at: March 4, 2026, 7:57 p.m.