Triple

T19998900
Position Surface form Disambiguated ID Type / Status
Subject How It’s Made E494266 entity
Predicate narrationBy P2181 FINISHED
Object Mark Douglas
Mark Douglas is a narrator known for his work on the documentary television series "How It’s Made."
 E1405386 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: Mark Douglas | Statement: [How It’s Made, narrationBy, Mark Douglas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mark Douglas
Context triple: [How It’s Made, narrationBy, Mark Douglas]
  • A. Don Harvey
    Don Harvey is an American character actor known for his intense supporting roles in films such as the Vietnam War drama "Casualties of War."
  • B. Keith Raniere
    Keith Raniere is the founder of the self-improvement organization NXIVM, which was later exposed as a cult involved in sex trafficking and racketeering.
  • C. Michael Fresco
    Michael Fresco is a television producer and director known for his work on various American TV series.
  • D. Ed Kemper
    Ed Kemper is an American serial killer and necrophile, known for murdering his grandparents, mother, and several young women in the 1960s and 1970s, and for later cooperating extensively with FBI profilers.
  • E. Matthew Diamond
    Matthew Diamond is an American director and choreographer known for his work in television, film, and stage productions.
  • 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: Mark Douglas
Triple: [How It’s Made, narrationBy, Mark Douglas]
Generated description
Mark Douglas is a narrator known for his work on the documentary television series "How It’s Made."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mark Douglas
Target entity description: Mark Douglas is a narrator known for his work on the documentary television series "How It’s Made."
  • A. Don Harvey
    Don Harvey is an American character actor known for his intense supporting roles in films such as the Vietnam War drama "Casualties of War."
  • B. Keith Raniere
    Keith Raniere is the founder of the self-improvement organization NXIVM, which was later exposed as a cult involved in sex trafficking and racketeering.
  • C. Michael Fresco
    Michael Fresco is a television producer and director known for his work on various American TV series.
  • D. Ed Kemper
    Ed Kemper is an American serial killer and necrophile, known for murdering his grandparents, mother, and several young women in the 1960s and 1970s, and for later cooperating extensively with FBI profilers.
  • E. Matthew Diamond
    Matthew Diamond is an American director and choreographer known for his work in television, film, and stage productions.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e661a09bdc819083305b08a11c6e34 completed April 20, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a080509d0748190a2703a2e3ddb0fc1 completed May 16, 2026, 5:47 a.m.
NEDg Description generation batch_6a0806563e1c8190b702fcfc009c84d5 completed May 16, 2026, 5:53 a.m.
NED2 Entity disambiguation (via description) batch_6a0806e876c881909f0c30e5dd16ce20 completed May 16, 2026, 5:55 a.m.
Created at: April 11, 2026, 3:32 p.m.