Triple

T5448328
Position Surface form Disambiguated ID Type / Status
Subject The Tower of London E122304 entity
Predicate city P40 FINISHED
Object City of London E19087 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: City of London | Statement: [The Tower of London, city, City of London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of London
Context triple: [The Tower of London, city, City of London]
  • A. City of London chosen
    The City of London is the historic and financial core of Greater London, renowned as one of the world’s leading global finance and business centers.
  • B. Westminster
    Westminster is a suburban city in the Denver metropolitan area of Colorado, known for its residential communities, parks, and proximity to the Rocky Mountains.
  • C. Westminster
    Westminster is a city in Orange County, California, known for its large Vietnamese-American community and vibrant Little Saigon district.
  • D. Westminster
    Westminster is a city in northern Maryland that serves as the county seat of Carroll County and a regional hub for the surrounding communities.
  • E. City of Westminster
    The City of Westminster is a central London borough that serves as the political and ceremonial heart of the United Kingdom, encompassing landmarks such as the Houses of Parliament, Buckingham Palace, and major government institutions.
  • 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_69bd4640f52c81909e653ec361f66d76 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91dbfd948190977513cf274af417 completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4883bfec8190bb09fff99d017111 completed March 22, 2026, 1:40 a.m.
Created at: March 20, 2026, 2:07 p.m.