Triple

T20610041
Position Surface form Disambiguated ID Type / Status
Subject Silk E506423 entity
Predicate mainCharacter P1183 FINISHED
Object Alan Cowdrey
Alan Cowdrey is the central fictional barrister protagonist in the British legal drama series "Silk."
E1454498 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: Alan Cowdrey | Statement: [Silk, mainCharacter, Alan Cowdrey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alan Cowdrey
Context triple: [Silk, mainCharacter, Alan Cowdrey]
  • A. Michael Gwynn
    Michael Gwynn was a British character actor known for his roles in mid-20th-century film and television, including appearances in classic horror and science fiction productions.
  • B. Clive Cheesman
    Clive Cheesman is a British herald and officer of arms known for his work in heraldry and genealogy at the College of Arms in London.
  • C. Clive Brook
    Clive Brook was a British film actor best known as a suave leading man in early Hollywood and British cinema during the 1920s and 1930s.
  • D. Ray Norton
    Ray Norton was an American sprinter and Olympic medalist known for being one of the world's fastest men in the late 1950s and early 1960s.
  • E. John Griffeth
    John Griffeth is best known as the husband of American singer and entertainer Deana Martin, daughter of legendary performer Dean Martin.
  • 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: Alan Cowdrey
Triple: [Silk, mainCharacter, Alan Cowdrey]
Generated description
Alan Cowdrey is the central fictional barrister protagonist in the British legal drama series "Silk."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alan Cowdrey
Target entity description: Alan Cowdrey is the central fictional barrister protagonist in the British legal drama series "Silk."
  • A. Michael Gwynn
    Michael Gwynn was a British character actor known for his roles in mid-20th-century film and television, including appearances in classic horror and science fiction productions.
  • B. Clive Cheesman
    Clive Cheesman is a British herald and officer of arms known for his work in heraldry and genealogy at the College of Arms in London.
  • C. Clive Brook
    Clive Brook was a British film actor best known as a suave leading man in early Hollywood and British cinema during the 1920s and 1930s.
  • D. Ray Norton
    Ray Norton was an American sprinter and Olympic medalist known for being one of the world's fastest men in the late 1950s and early 1960s.
  • E. John Griffeth
    John Griffeth is best known as the husband of American singer and entertainer Deana Martin, daughter of legendary performer Dean Martin.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aad6f53481908fb242947dda7028 completed April 20, 2026, 10:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a090aeae39881909a35767b9b57eab4 completed May 17, 2026, 12:25 a.m.
NEDg Description generation batch_6a090fb735cc8190a1dfea82584b7675 completed May 17, 2026, 12:45 a.m.
NED2 Entity disambiguation (via description) batch_6a091010ef9c8190862283f739b7027b completed May 17, 2026, 12:47 a.m.
Created at: April 16, 2026, 11:41 a.m.