Triple

T18915739
Position Surface form Disambiguated ID Type / Status
Subject Bloomberg SPACE, Walbrook E462719 entity
Predicate near P350 FINISHED
Object Mansion House 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: Mansion House | Statement: [Bloomberg SPACE, Walbrook, near, Mansion House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mansion House
Context triple: [Bloomberg SPACE, Walbrook, near, Mansion House]
  • A. Mansion House chosen
    Mansion House is the official residence and office of the Lord Mayor of London, located in the City of London.
  • B. York House
    York House was the former name of Bridgewater House, a grand aristocratic townhouse in central London historically associated with the British nobility.
  • C. York House
    York House is a historic riverside mansion and public garden in Twickenham, London, noted for its ornate architecture and famous Italianate statues.
  • D. York House
    York House is a historic wing within the St James's Palace complex in central London, traditionally associated with members of the British royal family.
  • E. Muswell Manor
    Muswell Manor is a historic manor house on the Isle of Sheppey in Kent, England, notable for its heritage significance and longstanding presence in the 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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c62685408190b17280147e1c247a completed April 20, 2026, 6:22 a.m.
Created at: April 10, 2026, 11:58 a.m.