Triple

T11909256
Position Surface form Disambiguated ID Type / Status
Subject Tower Hill E283350 entity
Predicate hasEntranceOn P1974 FINISHED
Object Trinity Square E105379 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: Trinity Square | Statement: [Tower Hill, hasEntranceOn, Trinity Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trinity Square
Context triple: [Tower Hill, hasEntranceOn, Trinity Square]
  • A. Trinity Square chosen
    Trinity Square is a historic public square in the City of London, known for its memorials and proximity to the Tower of London.
  • B. Charterhouse Square
    Charterhouse Square is a historic garden square in the Smithfield area of central London, known for its mix of academic, medical, and residential buildings.
  • C. Cabot Square
    Cabot Square is a historic urban public square and green space in downtown Montreal, known as a gathering place and transit hub near the Atwater area.
  • D. Cabot Square
    Cabot Square is a prominent landscaped plaza and fountain-centered public space within London’s Canary Wharf financial district.
  • E. Temple Bar Square
    Temple Bar Square is a central public plaza in Dublin’s cultural Temple Bar district, known for its lively atmosphere, street performances, and surrounding pubs, galleries, and cafes.
  • 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_69d6ab2c07e88190ba13b0d21fd6cf33 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8e5278eb081909a7ecfe38beeeda9 completed April 10, 2026, 11:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69f48a61e120819089e44568ce7e99fe completed May 1, 2026, 11:11 a.m.
Created at: April 8, 2026, 9:44 p.m.