Triple

T20912025
Position Surface form Disambiguated ID Type / Status
Subject Sir Julian Bullard E514971 entity
Predicate familyName P18 FINISHED
Object Bullard
Bullard is an English surname borne by various notable figures, including diplomats, politicians, and artists.
 E1456350 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: Bullard | Statement: [Sir Julian Bullard, familyName, Bullard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bullard
Context triple: [Sir Julian Bullard, familyName, Bullard]
  • A. Buckley
    Buckley is a surname most prominently associated with William F. Buckley Jr., the influential American conservative author and founder of National Review.
  • B. Buckley
    Buckley is a small city in Washington State known for its rural character and proximity to Mount Rainier.
  • C. Buckley
    Buckley is a small town in Flintshire, northeast Wales, known historically for its brickworks and coal mining industries.
  • D. Hulbert
    Hulbert is a small rural community located within the Township of South Dundas in eastern Ontario, Canada.
  • E. Burkett
    Burkett is a surname most notably associated with Jesse Burkett, a Hall of Fame Major League Baseball outfielder from the late 19th and early 20th centuries.
  • 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: Bullard
Triple: [Sir Julian Bullard, familyName, Bullard]
Generated description
Bullard is an English surname borne by various notable figures, including diplomats, politicians, and artists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bullard
Target entity description: Bullard is an English surname borne by various notable figures, including diplomats, politicians, and artists.
  • A. Buckley
    Buckley is a surname most prominently associated with William F. Buckley Jr., the influential American conservative author and founder of National Review.
  • B. Buckley
    Buckley is a small town in Flintshire, northeast Wales, known historically for its brickworks and coal mining industries.
  • C. Buckley
    Buckley is a small city in Washington State known for its rural character and proximity to Mount Rainier.
  • D. Hulbert
    Hulbert is a small rural community located within the Township of South Dundas in eastern Ontario, Canada.
  • E. Burkett
    Burkett is a surname most notably associated with Jesse Burkett, a Hall of Fame Major League Baseball outfielder from the late 19th and early 20th centuries.
  • 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_69e0b4f9d5ec8190bb2bd27350ed341c completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6ec5f5bc48190a8e7e6af60b158fb completed April 21, 2026, 3:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0918de5fd08190a5138fdc10898c4f completed May 17, 2026, 1:24 a.m.
NEDg Description generation batch_6a091993208c81908fa52d9df76bc3e4 completed May 17, 2026, 1:27 a.m.
NED2 Entity disambiguation (via description) batch_6a0919f58008819097e05a187ed4b3de completed May 17, 2026, 1:29 a.m.
Created at: April 16, 2026, 12:48 p.m.