Triple

T1902167
Position Surface form Disambiguated ID Type / Status
Subject London Cannon Street E37712 entity
Predicate nearbyLandmark P350 FINISHED
Object Mansion House E104810 NE FINISHED

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: [London Cannon Street, nearbyLandmark, Mansion House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mansion House
Context triple: [London Cannon Street, nearbyLandmark, 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 is a historic wing within the St James's Palace complex in central London, traditionally associated with members of the British royal family.
  • C. 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.
  • D. Henry House
    Henry House is a historic home and key landmark on the Manassas National Battlefield in Virginia, associated with major Civil War fighting.
  • E. Regent House
    Regent House is the principal governing body of the University of Cambridge, comprising its senior academic and administrative staff who make key decisions on university policy and governance.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a8861be7148190a680937ec451a304 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb18f10e48190b2f8c64c42cc55f3 completed March 7, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3d0d01c8190ae0c8029fead4008 completed March 8, 2026, 10:10 p.m.
Created at: March 4, 2026, 7:35 p.m.