Triple

T2360100
Position Surface form Disambiguated ID Type / Status
Subject Aquatic Park E47250 entity
Predicate hasAccessFrom P1985 FINISHED
Object Hyde Street E29954 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: Hyde Street | Statement: [Aquatic Park, hasAccessFrom, Hyde Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hyde Street
Context triple: [Aquatic Park, hasAccessFrom, Hyde Street]
  • A. Hyde Street chosen
    Hyde Street is a well-known thoroughfare in San Francisco, famous for its steep hills, scenic views, and role as a popular route for the city’s historic cable cars.
  • B. Hart Street
    Hart Street is a historic street in the City of London, known for landmarks such as the medieval St Olave's Church.
  • C. Forrester Street
    Forrester Street is a roadway in Salem, Massachusetts, that runs along the edge of the historic Salem Common park.
  • D. Harrison Street
    Harrison Street is a major thoroughfare in Oakland, California, running through areas including the historic Chinatown neighborhood.
  • E. Hampshire Street
    Hampshire Street is a roadway in Cambridge, Massachusetts, that runs through the Inman Square neighborhood and connects it with other parts of the city.
  • 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_69a88a1a4a6081908645b0f2914521ab completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc722ac3c819091f4316a4a166a77 completed March 7, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69bb60bff62881908ff53b9b02d9c869 completed March 19, 2026, 2:34 a.m.
Created at: March 4, 2026, 7:55 p.m.