Triple

T1252187
Position Surface form Disambiguated ID Type / Status
Subject Red Dust E26901 entity
Predicate basedOnWorkBy P2806 FINISHED
Object Wilson Collison
Wilson Collison was an American playwright and novelist whose works, often adapted for stage and screen, contributed to early 20th-century popular entertainment.
 E214428 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: Wilson Collison | Statement: [Red Dust, basedOnWorkBy, Wilson Collison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wilson Collison
Context triple: [Red Dust, basedOnWorkBy, Wilson Collison]
  • A. Jack Colwell
    Jack Colwell is known primarily as the husband of prominent American microbiologist and former NSF director Rita R. Colwell.
  • B. Adrian Biddle
    Adrian Biddle was a British cinematographer known for his visually striking work on films such as "Aliens," "Thelma & Louise," and "The Mummy."
  • C. Andrew Humphrey
    Andrew Humphrey was a senior Royal Air Force officer who rose to become Chief of the Air Staff and later Chief of the Defence Staff in the United Kingdom.
  • D. Richard Hiscott
    Richard Hiscott is an editor known for his work on the television series "Willow."
  • E. Colin Bond
    Colin Bond is an Australian former racing driver and team manager best known for his success in touring car and rally competition during the 1960s and 1970s.
  • 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: Wilson Collison
Triple: [Red Dust, basedOnWorkBy, Wilson Collison]
Generated description
Wilson Collison was an American playwright and novelist whose works, often adapted for stage and screen, contributed to early 20th-century popular entertainment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wilson Collison
Target entity description: Wilson Collison was an American playwright and novelist whose works, often adapted for stage and screen, contributed to early 20th-century popular entertainment.
  • A. Jack Colwell
    Jack Colwell is known primarily as the husband of prominent American microbiologist and former NSF director Rita R. Colwell.
  • B. Adrian Biddle
    Adrian Biddle was a British cinematographer known for his visually striking work on films such as "Aliens," "Thelma & Louise," and "The Mummy."
  • C. Andrew Humphrey
    Andrew Humphrey was a senior Royal Air Force officer who rose to become Chief of the Air Staff and later Chief of the Defence Staff in the United Kingdom.
  • D. Richard Hiscott
    Richard Hiscott is an editor known for his work on the television series "Willow."
  • E. Colin Bond
    Colin Bond is an Australian former racing driver and team manager best known for his success in touring car and rally competition during the 1960s and 1970s.
  • 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_69a49487a9c48190ba9b05348fd1b53f completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4bf875cf48190b6781d41097ee39b completed March 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69adf3ab00888190afc7c54d9b89ae3b completed March 8, 2026, 10:09 p.m.
NEDg Description generation batch_69adf452ab488190b5d57e3b04159408 completed March 8, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69adf4bdb6dc8190964e5e78abfb8e40 completed March 8, 2026, 10:14 p.m.
Created at: March 1, 2026, 7:47 p.m.