Triple

T18124930
Position Surface form Disambiguated ID Type / Status
Subject Windsor, Maine E433845 entity
Predicate isInCountySeatOf P14649 FINISHED
Object Augusta, Maine 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: Augusta, Maine | Statement: [Windsor, Maine, isInCountySeatOf, Augusta, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Augusta, Maine
Context triple: [Windsor, Maine, isInCountySeatOf, Augusta, Maine]
  • A. Augusta, Maine chosen
    Augusta, Maine is a small city in the northeastern United States known as the capital of the state of Maine and situated along the Kennebec River.
  • B. Monroe, Maine
    Monroe, Maine is a small rural town in Waldo County known for its quiet countryside and close-knit community in central coastal Maine.
  • C. Portland, Maine
    Portland, Maine is a coastal New England city known for its historic Old Port district, vibrant arts and food scenes, and working waterfront on Casco Bay.
  • D. Hartford, Maine
    Hartford, Maine is a small rural town in Oxford County known for its forests, lakes, and quiet residential character in western Maine.
  • E. Washington, Maine
    Washington, Maine is a small rural town in Knox County known for its lakes, forests, and quiet New England character.
  • 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_69d8b909e8cc81908df4cc2b8ea6d11f completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dded1bd4819080fa362e88c921cf completed April 19, 2026, 1:51 p.m.
Created at: April 10, 2026, 10:28 a.m.