Triple

T6050716
Position Surface form Disambiguated ID Type / Status
Subject Copley E134784 entity
Predicate hasEntrance P6140 FINISHED
Object Boylston Street E22719 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: Boylston Street | Statement: [Copley, hasEntrance, Boylston Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boylston Street
Context triple: [Copley, hasEntrance, Boylston Street]
  • A. Boylston Street, Boston chosen
    Boylston Street in Boston is a major downtown thoroughfare best known as the iconic finish-line location of the Boston Marathon.
  • B. Brattle Street
    Brattle Street is a historic thoroughfare in Cambridge, Massachusetts, known for its colonial-era houses, cultural landmarks, and proximity to Harvard University.
  • C. Harvard Street
    Harvard Street is a major thoroughfare in Brookline, Massachusetts, lined with shops, restaurants, and residential buildings and serving as a key local commercial corridor.
  • D. Winthrop Street
    Winthrop Street is a New York City Subway station in Brooklyn served by the 2 and 5 trains.
  • E. Beacon Street
    Beacon Street is a street in Lichfield, Staffordshire, England, known for its historic buildings including the former home of physician and poet Erasmus Darwin.
  • 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_69c00877b6d4819096b0e163728b73a3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056f66cb08190a782cdd038f26b93 completed March 22, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c243af0a108190a315314376332ec6 completed March 24, 2026, 7:56 a.m.
Created at: March 22, 2026, 4:09 p.m.