Triple

T20926039
Position Surface form Disambiguated ID Type / Status
Subject Kensington Girls' School E515345 entity
Predicate locatedIn P40 FINISHED
Object Kensington 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: Kensington | Statement: [Kensington Girls' School, locatedIn, Kensington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kensington
Context triple: [Kensington Girls' School, locatedIn, Kensington]
  • A. Kensington chosen
    Kensington is a district in West London, England, known for its affluent residential areas, cultural institutions, and royal associations.
  • B. Kensington
    Kensington is a small, affluent unincorporated community in Contra Costa County, California, located in the San Francisco Bay Area.
  • C. Kensington
    Kensington is a historic Philadelphia neighborhood known for its industrial past and ongoing urban redevelopment.
  • D. Kensington
    Kensington is an inner-city suburb of Melbourne, Victoria, known for its mix of historic workers’ cottages, industrial heritage, and growing residential developments close to the central business district.
  • E. Kensington
    Kensington is a residential suburb within the City of Swan in Western Australia, known for its local community amenities and proximity to Perth’s urban areas.
  • 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_69e0b4fb431c8190b9d40e6a72f0cc87 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6f65200b08190ac208204a20f5a6a completed April 21, 2026, 4 a.m.
Created at: April 16, 2026, 12:49 p.m.