Triple

T19931349
Position Surface form Disambiguated ID Type / Status
Subject Haymarket E479060 entity
Predicate hasNearbyStreet P8235 FINISHED
Object Regent 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: Regent Street | Statement: [Haymarket, hasNearbyStreet, Regent Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Regent Street
Context triple: [Haymarket, hasNearbyStreet, Regent Street]
  • A. Regent Street chosen
    Regent Street is a major shopping and commercial thoroughfare in London’s West End, renowned for its elegant architecture and flagship retail stores.
  • B. Regent Street
    Regent Street is a central street in Cambridge, England, known for its mix of university buildings, shops, and access to key city thoroughfares.
  • C. Regent Street
    Regent Street is a key thoroughfare in the Sydney suburb of Kogarah, serving as an important local commercial and traffic route.
  • D. Mortimer Street
    Mortimer Street is a central London street in the Fitzrovia area, known for its mix of historic and modern buildings, offices, and medical facilities.
  • E. Holborn Road
    Holborn Road is a major commercial street in New Kingston, Jamaica, known for its offices, hotels, and proximity to key business and shopping 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a13ebc08190a583aa4c5e9f6648 completed April 20, 2026, 4:53 p.m.
Created at: April 10, 2026, 1:53 p.m.