Triple

T10493779
Position Surface form Disambiguated ID Type / Status
Subject Blow Out E247482 entity
Predicate hasCastMember P2308 FINISHED
Object Peter Boyden
Peter Boyden is an actor known for appearing in the 1981 thriller film "Blow Out."
E867697 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: Peter Boyden | Statement: [Blow Out, hasCastMember, Peter Boyden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Boyden
Context triple: [Blow Out, hasCastMember, Peter Boyden]
  • A. Peter Bowker
    Peter Bowker is a British television and film screenwriter known for creating and writing acclaimed dramas such as "Blackpool," "Occupation," and "World on Fire."
  • B. Peter Dougherty
    Peter Dougherty was a television producer and director best known for co-creating and shaping the influential hip-hop music video program "Yo! MTV Raps."
  • C. Paul Reynolds
    Paul Reynolds is a New Zealand politician and former chief executive of Telecom New Zealand, known for leading the company through major structural and technological changes.
  • D. Paul Millspaugh
    Paul Millspaugh is a film editor known for his work on the romantic comedy "Two Can Play That Game."
  • E. Keith Peters
    Keith Peters is a prominent British physician and medical researcher known for his leadership in academic medicine and contributions to immunology and medical science policy.
  • 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: Peter Boyden
Triple: [Blow Out, hasCastMember, Peter Boyden]
Generated description
Peter Boyden is an actor known for appearing in the 1981 thriller film "Blow Out."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Peter Boyden
Target entity description: Peter Boyden is an actor known for appearing in the 1981 thriller film "Blow Out."
  • A. Peter Bowker
    Peter Bowker is a British television and film screenwriter known for creating and writing acclaimed dramas such as "Blackpool," "Occupation," and "World on Fire."
  • B. Peter Dougherty
    Peter Dougherty was a television producer and director best known for co-creating and shaping the influential hip-hop music video program "Yo! MTV Raps."
  • C. Paul Reynolds
    Paul Reynolds is a New Zealand politician and former chief executive of Telecom New Zealand, known for leading the company through major structural and technological changes.
  • D. Paul Millspaugh
    Paul Millspaugh is a film editor known for his work on the romantic comedy "Two Can Play That Game."
  • E. Keith Peters
    Keith Peters is a prominent British physician and medical researcher known for his leadership in academic medicine and contributions to immunology and medical science policy.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5097fe2bc81909d66ce43f3533284 completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dcaeb6088190829b6c26eb1de7d5 completed April 10, 2026, 11:19 a.m.
NEDg Description generation batch_69d8e8c8e360819085376d4c4ea9712d completed April 10, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69d901ef24608190934377d9dc855d6f completed April 10, 2026, 1:58 p.m.
Created at: April 6, 2026, 12:24 p.m.