Triple

T20350673
Position Surface form Disambiguated ID Type / Status
Subject Deep Blue E495996 entity
Predicate editingBy P1954 FINISHED
Object Martin Elsbury
Martin Elsbury is a film editor best known for his work on the chess-themed film "Deep Blue."
 E1432313 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: Martin Elsbury | Statement: [Deep Blue, editingBy, Martin Elsbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Martin Elsbury
Context triple: [Deep Blue, editingBy, Martin Elsbury]
  • A. Alec Troup
    Alec Troup was a Scottish professional footballer known for playing as a winger in the early 20th century.
  • B. Giles Townsend
    Giles Townsend is a member of the Townsend family, known primarily as a son of British Royal Air Force officer and royal associate Peter Wooldridge Townsend.
  • C. Geoffrey Bayldon
    Geoffrey Bayldon was an English character actor best known for his eccentric roles in British film and television, particularly as the title character in the children's series "Catweazle."
  • D. Peter Yeldham
    Peter Yeldham was an Australian screenwriter and playwright known for his prolific work in film, television, and radio from the mid-20th century onward.
  • E. James Elmes
    James Elmes was a 19th-century English architect, civil engineer, and writer known for his architectural criticism and editorship of the Annals of the Fine Arts.
  • 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: Martin Elsbury
Triple: [Deep Blue, editingBy, Martin Elsbury]
Generated description
Martin Elsbury is a film editor best known for his work on the chess-themed film "Deep Blue."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Martin Elsbury
Target entity description: Martin Elsbury is a film editor best known for his work on the chess-themed film "Deep Blue."
  • A. Alec Troup
    Alec Troup was a Scottish professional footballer known for playing as a winger in the early 20th century.
  • B. Giles Townsend
    Giles Townsend is a member of the Townsend family, known primarily as a son of British Royal Air Force officer and royal associate Peter Wooldridge Townsend.
  • C. Geoffrey Bayldon
    Geoffrey Bayldon was an English character actor best known for his eccentric roles in British film and television, particularly as the title character in the children's series "Catweazle."
  • D. Peter Yeldham
    Peter Yeldham was an Australian screenwriter and playwright known for his prolific work in film, television, and radio from the mid-20th century onward.
  • E. James Elmes
    James Elmes was a 19th-century English architect, civil engineer, and writer known for his architectural criticism and editorship of the Annals of the Fine Arts.
  • 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_69e0b4a3320881909495ae8bc30bc2dc completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6784f8ff48190a070888786f6a989 completed April 20, 2026, 7:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a088afea7388190b799a3692b2226d1 completed May 16, 2026, 3:19 p.m.
NEDg Description generation batch_6a088bc432008190943421af77787f55 completed May 16, 2026, 3:22 p.m.
NED2 Entity disambiguation (via description) batch_6a088c42288c8190805bdbe6e8ef184b completed May 16, 2026, 3:24 p.m.
Created at: April 16, 2026, 11:24 a.m.