Triple

T22556655
Position Surface form Disambiguated ID Type / Status
Subject NoLita E557702 entity
Predicate hasStreet P959 FINISHED
Object Elizabeth 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: Elizabeth Street | Statement: [NoLita, hasStreet, Elizabeth Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Street
Context triple: [NoLita, hasStreet, Elizabeth Street]
  • A. Elizabeth Street chosen
    Elizabeth Street is a major thoroughfare in central Sydney, Australia, running along the eastern edge of the CBD and adjacent to Hyde Park.
  • B. Chelsea Street
    Chelsea Street is a major thoroughfare in Chelsea, Massachusetts that serves as a key corridor for traffic and public transit between Chelsea and Boston.
  • C. Brighton Street
    Brighton Street is a road in Wallasey, Merseyside, England, known for being the location of Wallasey Town Hall.
  • D. Jellicoe Street
    Jellicoe Street is a waterfront street in Auckland, New Zealand, known for its proximity to the redeveloped Wynyard Quarter and North Wharf dining and entertainment precinct.
  • E. Rachel Street
    Rachel Street is a notable thoroughfare in Montreal, Quebec, running through the vibrant Le Plateau-Mont-Royal borough and known for its mix of residential areas, local shops, and access to nearby parks.
  • 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_69e11e59db848190b4272ecd2b690ffd completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f7a4a3c81908fc87f48b6dcbbf7 completed April 29, 2026, 1:31 a.m.
Created at: April 16, 2026, 8:52 p.m.