Triple

T11589889
Position Surface form Disambiguated ID Type / Status
Subject Portsmouth Harbor E274852 entity
Predicate adjacentTown P3883 FINISHED
Object Kittery, 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: Kittery, Maine | Statement: [Portsmouth Harbor, adjacentTown, Kittery, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kittery, Maine
Context triple: [Portsmouth Harbor, adjacentTown, Kittery, Maine]
  • A. Kittery, Maine chosen
    Kittery, Maine is a historic coastal town at the southern tip of the state, known for its naval shipyard and outlet shopping district.
  • B. Kennebunk, Maine
    Kennebunk, Maine is a coastal New England town known for its historic charm, beaches, and popular summer tourism.
  • C. Searsport, Maine
    Searsport, Maine is a small coastal town in New England known for its historic deep-water port and maritime heritage.
  • D. Knox, Maine
    Knox, Maine is a small rural town located in Waldo County in the state of Maine, United States.
  • 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 (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_69d6aae6b14c81908dc5a74bad7591f9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d894643ae48190837502b713f5b9c6 completed April 10, 2026, 6:10 a.m.
Created at: April 8, 2026, 9:38 p.m.