Triple

T19556178
Position Surface form Disambiguated ID Type / Status
Subject John Bercow E489317 entity
Predicate familyName P18 FINISHED
Object Bercow
Bercow is a British surname most prominently associated with John Bercow, the former Speaker of the UK House of Commons.
E1384062 NE FINISHED

How this triple was built (4 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: Bercow | Statement: [John Bercow, familyName, Bercow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bercow
Context triple: [John Bercow, familyName, Bercow]
  • A. Boothby
    Boothby is an Australian federal electoral division in South Australia that covers parts of Adelaide’s inner southern suburbs.
  • B. Acton Turville
    Acton Turville is a small rural village and civil parish in South Gloucestershire, England, near the border with Wiltshire.
  • C. Bardwell
    Bardwell is a small city in western Kentucky that serves as the administrative and governmental center of Carlisle County.
  • D. Bardwell
    Bardwell is a small rural village and civil parish in the county of Suffolk in eastern England.
  • E. Wycombe
    Wycombe is a UK parliamentary constituency in Buckinghamshire, represented in the House of Commons and centered on the town of High Wycombe.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bercow
Triple: [John Bercow, familyName, Bercow]
Generated description
Bercow is a British surname most prominently associated with John Bercow, the former Speaker of the UK House of Commons.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bercow
Target entity description: Bercow is a British surname most prominently associated with John Bercow, the former Speaker of the UK House of Commons.
  • A. Boothby
    Boothby is an Australian federal electoral division in South Australia that covers parts of Adelaide’s inner southern suburbs.
  • B. Acton Turville
    Acton Turville is a small rural village and civil parish in South Gloucestershire, England, near the border with Wiltshire.
  • C. Bardwell
    Bardwell is a small city in western Kentucky that serves as the administrative and governmental center of Carlisle County.
  • D. Bardwell
    Bardwell is a small rural village and civil parish in the county of Suffolk in eastern England.
  • E. Wycombe
    Wycombe is a UK parliamentary constituency in Buckinghamshire, represented in the House of Commons and centered on the town of High Wycombe.
  • F. None of above. chosen

Provenance (5 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d341d708190b8ef35822f8bfe7c completed April 20, 2026, 2:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07577e66c4819080298e223c2ece16 completed May 15, 2026, 5:27 p.m.
NEDg Description generation batch_6a07583fc26481908bd2f00c19f3b4cd completed May 15, 2026, 5:30 p.m.
NED2 Entity disambiguation (via description) batch_6a07594a23ac81908807df4605555d3f completed May 15, 2026, 5:35 p.m.
Created at: April 10, 2026, 1:42 p.m.