Triple

T22556656
Position Surface form Disambiguated ID Type / Status
Subject NoLita E557702 entity
Predicate hasStreet P959 FINISHED
Object Prince 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: Prince Street | Statement: [NoLita, hasStreet, Prince Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prince Street
Context triple: [NoLita, hasStreet, Prince Street]
  • A. Prince Street
    Prince Street is a historic, cobblestone-lined thoroughfare in Old Town Alexandria, Virginia, known for its preserved 18th- and 19th-century architecture and waterfront access.
  • B. Prince Street
    Prince Street is a historic thoroughfare in Bristol, England, known for its proximity to the city’s harbourside and its association with the Prince Street Bridge.
  • C. Prince Street
    Prince Street is a short-lived American television drama series centered on an undercover NYPD unit operating in New York City.
  • D. Prince Street chosen
    Prince Street is a New York City Subway station in Manhattan’s SoHo neighborhood, served by Broadway Line trains and providing access to nearby shopping and cultural attractions.
  • E. Queen Street
    Queen Street is the main commercial and retail thoroughfare in central Auckland, New Zealand, known for its shops, offices, and entertainment venues.
  • 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.