Triple

T2266448
Position Surface form Disambiguated ID Type / Status
Subject Arlington station E50155 entity
Predicate locatedOn P40 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: [Arlington station, locatedOn, Boylston Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boylston Street
Context triple: [Arlington station, locatedOn, 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. Winthrop Street
    Winthrop Street is a New York City Subway station in Brooklyn served by the 2 and 5 trains.
  • D. Beacon Street
    Beacon Street is a historic thoroughfare in Boston, Massachusetts, known for running along the Boston Common and past prominent landmarks in the Beacon Hill neighborhood.
  • E. Tremont Street, Boston
    Tremont Street in Boston is a major historic thoroughfare running through downtown and bordering Boston Common, lined with notable civic, cultural, and commercial landmarks.
  • 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_69a88b01e0048190ba96431b5f990ba9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc18fff0c8190acd73d8db8a41cff completed March 7, 2026, 6:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71d492a48190be58396831e87ea0 completed March 9, 2026, 7:08 a.m.
Created at: March 4, 2026, 7:48 p.m.