Triple

T17295921
Position Surface form Disambiguated ID Type / Status
Subject Ashburnham, Massachusetts E419909 entity
Predicate namedAfter P63 FINISHED
Object John Ashburnham
John Ashburnham was an English royalist and courtier closely associated with King Charles I during the English Civil War.
E1261697 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: John Ashburnham | Statement: [Ashburnham, Massachusetts, namedAfter, John Ashburnham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Ashburnham
Context triple: [Ashburnham, Massachusetts, namedAfter, John Ashburnham]
  • A. Bob Scott
    Bob Scott was an Australian rules football field umpire best known for officiating the 1934 Victorian Football League Grand Final.
  • B. Tom Hughes
    Tom Hughes is a person known primarily as the stepchild of former Australian cricketer Kim Hughes.
  • C. Tom Hughes
    Tom Hughes is a British actor known for his roles in film and television, including period dramas and contemporary comedies.
  • D. Tom Hughes
    Tom Hughes was an early 20th-century Major League Baseball pitcher best known for his standout season with the Boston Americans in 1903.
  • E. Harold H. Burton
    Harold H. Burton was an American jurist and politician who served as an Associate Justice of the U.S. Supreme Court from 1945 to 1958.
  • 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: John Ashburnham
Triple: [Ashburnham, Massachusetts, namedAfter, John Ashburnham]
Generated description
John Ashburnham was an English royalist and courtier closely associated with King Charles I during the English Civil War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Ashburnham
Target entity description: John Ashburnham was an English royalist and courtier closely associated with King Charles I during the English Civil War.
  • A. Bob Scott
    Bob Scott was an Australian rules football field umpire best known for officiating the 1934 Victorian Football League Grand Final.
  • B. Tom Hughes
    Tom Hughes was an early 20th-century Major League Baseball pitcher best known for his standout season with the Boston Americans in 1903.
  • C. Tom Hughes
    Tom Hughes is a British actor known for his roles in film and television, including period dramas and contemporary comedies.
  • D. Tom Hughes
    Tom Hughes is a person known primarily as the stepchild of former Australian cricketer Kim Hughes.
  • E. Harold H. Burton
    Harold H. Burton was an American jurist and politician who served as an Associate Justice of the U.S. Supreme Court from 1945 to 1958.
  • 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_69d886db32608190a61e18862c5a8af6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e437875b208190bcf0df2ded546257 completed April 19, 2026, 2:01 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0180d881ec81908e794143d355effe completed May 11, 2026, 7:10 a.m.
NEDg Description generation batch_6a0185288b0c8190aa2122b40f2f5722 completed May 11, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_6a0185bd6e0c8190be703e260c499b5e completed May 11, 2026, 7:31 a.m.
Created at: April 10, 2026, 5:40 a.m.