Triple

T22592998
Position Surface form Disambiguated ID Type / Status
Subject Charnwood E564997 entity
Predicate contains P35 FINISHED
Object Cossington 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: Cossington | Statement: [Charnwood, contains, Cossington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cossington
Context triple: [Charnwood, contains, Cossington]
  • A. Cossington chosen
    Cossington is a small village in Leicestershire, England, situated in the Soar Valley near the River Soar.
  • B. Bristol Beverley
    The Bristol Beverley was a large British military transport aircraft of the 1950s and 1960s, known for its high-wing, boxy fuselage design and rear-loading ramp for heavy cargo and paratroop operations.
  • C. Cranwell
    Cranwell is a village in Lincolnshire, England, best known for its historic Royal Air Force training college, RAF Cranwell.
  • D. Clewer
    Clewer is a suburban area and former village within the Royal Borough of Windsor and Maidenhead in Berkshire, England.
  • E. Linstow
    Linstow is a Norwegian family name most notably associated with architect Hans Ditlev Franciscus Linstow, designer of Oslo’s Royal Palace and key parts of the city’s urban plan.
  • 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f16163cb248190b377b110d80a6730 completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:49 p.m.