Triple

T13704486
Position Surface form Disambiguated ID Type / Status
Subject Park Street station E328604 entity
Predicate hasEntranceOn P1974 FINISHED
Object Park Street 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: Park Street | Statement: [Park Street station, hasEntranceOn, Park Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Park Street
Context triple: [Park Street station, hasEntranceOn, Park Street]
  • A. Park Street
    Park Street is a street located in the historic city centre of Cambridge, England, known for its proximity to university colleges and central amenities.
  • B. Park Street chosen
    Park Street is a major downtown Boston subway station and transfer hub on the Massachusetts Bay Transportation Authority (MBTA) system.
  • C. Park Street
    Park Street is a small village and residential community in Hertfordshire, England, situated near St Albans.
  • D. Park Street
    Park Street is one of the busiest and most prominent stations on the Kolkata Metro, serving the central commercial and entertainment district of the city.
  • E. Pratt Street
    Pratt Street is a major east–west thoroughfare in downtown Baltimore, Maryland, known for running through the city’s central business and Inner Harbor areas.
  • 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_69d8076ff62081908a7bd79889edd7a0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dcad17732c8190bbd0d73107711c99 completed April 13, 2026, 8:45 a.m.
Created at: April 9, 2026, 9:54 p.m.