Triple

T7329200
Position Surface form Disambiguated ID Type / Status
Subject Calendar Islands E168954 entity
Predicate nearbyTown P3883 FINISHED
Object Harpswell, Maine E354581 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: Harpswell, Maine | Statement: [Calendar Islands, nearbyTown, Harpswell, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harpswell, Maine
Context triple: [Calendar Islands, nearbyTown, Harpswell, Maine]
  • A. Harpswell, Maine chosen
    Harpswell, Maine is a coastal New England town known for its rugged shoreline, fishing heritage, and numerous islands and peninsulas along Casco Bay.
  • B. Southwest Harbor, Maine
    Southwest Harbor, Maine is a coastal town on Mount Desert Island known for its working waterfront, boatbuilding heritage, and proximity to Acadia National Park.
  • C. Hollis, Maine
    Hollis, Maine is a small rural town in southern Maine known for its residential character and location along the Saco River in York County.
  • D. North Haven, Maine
    North Haven, Maine is a small island town in Penobscot Bay known for its scenic coastal landscapes, fishing heritage, and seasonal tourism.
  • E. Shapleigh, Maine
    Shapleigh, Maine is a small rural town in southwestern Maine known for its forests, lakes, and outdoor recreation.
  • 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_69c68a54cacc81908e3b773441f19566 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0a9c0f081909218560d8a4f4995 completed March 27, 2026, 9:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69d05422b25c819098189ac202c20123 completed April 3, 2026, 11:58 p.m.
Created at: March 27, 2026, 3:03 p.m.