Triple

T13980279
Position Surface form Disambiguated ID Type / Status
Subject Presque Isle micropolitan area E336289 entity
Predicate contains P35 FINISHED
Object Stockholm, 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: Stockholm, Maine | Statement: [Presque Isle micropolitan area, contains, Stockholm, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stockholm, Maine
Context triple: [Presque Isle micropolitan area, contains, Stockholm, Maine]
  • A. Stockholm, Maine chosen
    Stockholm, Maine is a small rural town in northern Maine known for its Swedish heritage and location within Aroostook County.
  • B. Belgrade, Maine
    Belgrade, Maine is a small town in central Maine known for its scenic chain of lakes and rural New England character.
  • C. Oakland, Maine
    Oakland, Maine is a small town in central Maine known for its lakeside setting, residential character, and proximity to the city of Waterville.
  • D. Dresden, Maine
    Dresden, Maine is a small rural town in Lincoln County known for its historic character and scenic location along the Kennebec River.
  • E. 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.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ea10dc88190b9720919a021e570 completed April 14, 2026, 12:10 p.m.
Created at: April 9, 2026, 10:18 p.m.