Triple

T18281561
Position Surface form Disambiguated ID Type / Status
Subject Connecticut shoreline E437875 entity
Predicate hasTown P847 FINISHED
Object Guilford 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: Guilford | Statement: [Connecticut shoreline, hasTown, Guilford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guilford
Context triple: [Connecticut shoreline, hasTown, Guilford]
  • A. Guilford
    Guilford is a town located within the Windham Region of Vermont, known for its rural character and New England landscape.
  • B. Guilford
    Guilford is a British territorial designation historically associated with the noble title of Baron Guilford.
  • C. Guilford, Connecticut chosen
    Guilford, Connecticut is a historic coastal New England town on Long Island Sound known for its colonial architecture, town green, and shoreline community character.
  • D. Middletown
    Middletown is the sociological pseudonym for Muncie, Indiana, famously used in classic studies as a representative American small city.
  • E. Middletown
    Middletown is one of New Jersey’s oldest and largest suburban communities, known for its historic roots, residential neighborhoods, and proximity to the Jersey Shore.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50056ea0481908d66bf263ac80c75 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:35 a.m.