Triple

T17665761
Position Surface form Disambiguated ID Type / Status
Subject Threadneedle Street E440376 entity
Predicate hasJunctionWith P1018 FINISHED
Object Prince’s 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’s Street | Statement: [Threadneedle Street, hasJunctionWith, Prince’s Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prince’s Street
Context triple: [Threadneedle Street, hasJunctionWith, Prince’s Street]
  • A. Prince's Street chosen
    Prince's Street is a short street in the City of London, located in the historic financial district near the Bank of England.
  • B. Princes Street
    Princes Street is Edinburgh’s main shopping and thoroughfare street, famed for its views of Edinburgh Castle and the Old Town across Princes Street Gardens.
  • C. James’s Street
    James’s Street is a historic thoroughfare in Dublin, Ireland, known for housing major landmarks such as the Guinness-associated St. James’s Gate Brewery.
  • D. Princesa Street
    Princesa Street is a major thoroughfare in Madrid, Spain, known for its shops, cinemas, and connection between Plaza de España and the Argüelles area.
  • E. Erskine Street
    Erskine Street is a street in central Sydney, Australia, that connects the city’s central business district to the King Street Wharf waterfront area.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46ea9d91c81908414ef38c7fb36a4 completed April 19, 2026, 5:56 a.m.
Created at: April 10, 2026, 9:56 a.m.