Triple

T2325932
Position Surface form Disambiguated ID Type / Status
Subject Roman Holiday E48287 entity
Predicate editedBy P1954 FINISHED
Object Robert Swink
Robert Swink was an American film editor known for his work on numerous classic Hollywood films, including "Roman Holiday."
E255026 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: Robert Swink | Statement: [Roman Holiday, editedBy, Robert Swink]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Swink
Context triple: [Roman Holiday, editedBy, Robert Swink]
  • A. Gilbert Stork
    Gilbert Stork was a prominent 20th-century organic chemist renowned for pioneering methods in stereoselective synthesis and significantly advancing the field of synthetic organic chemistry.
  • B. Hans Bonte
    Hans Bonte is a Belgian politician known for serving as the mayor of Vilvoorde and as a member of the federal parliament.
  • C. Philip Steuer
    Philip Steuer is a film producer best known for his work on major studio projects, including the Disney drama "Saving Mr. Banks."
  • D. Ron Jensen
    Ron Jensen is an American politician who has served as the mayor of Grand Prairie, Texas.
  • E. John Dinkeloo
    John Dinkeloo was an American architect best known for his partnership with Eero Saarinen and later leadership of Kevin Roche John Dinkeloo and Associates, contributing to numerous influential modernist buildings.
  • 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: Robert Swink
Triple: [Roman Holiday, editedBy, Robert Swink]
Generated description
Robert Swink was an American film editor known for his work on numerous classic Hollywood films, including "Roman Holiday."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robert Swink
Target entity description: Robert Swink was an American film editor known for his work on numerous classic Hollywood films, including "Roman Holiday."
  • A. Gilbert Stork
    Gilbert Stork was a prominent 20th-century organic chemist renowned for pioneering methods in stereoselective synthesis and significantly advancing the field of synthetic organic chemistry.
  • B. Hans Bonte
    Hans Bonte is a Belgian politician known for serving as the mayor of Vilvoorde and as a member of the federal parliament.
  • C. Philip Steuer
    Philip Steuer is a film producer best known for his work on major studio projects, including the Disney drama "Saving Mr. Banks."
  • D. Ron Jensen
    Ron Jensen is an American politician who has served as the mayor of Grand Prairie, Texas.
  • E. John Dinkeloo
    John Dinkeloo was an American architect best known for his partnership with Eero Saarinen and later leadership of Kevin Roche John Dinkeloo and Associates, contributing to numerous influential modernist buildings.
  • 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_69a88aa308a88190b0b86c011fda7fce completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc64b62a08190b5a415769ce42645 completed March 7, 2026, 6:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae897004308190bc2e335e9caea2ca completed March 9, 2026, 8:48 a.m.
NEDg Description generation batch_69ae8ace309c8190b57426d1449de723 completed March 9, 2026, 8:54 a.m.
NED2 Entity disambiguation (via description) batch_69ae8b56d8548190aa6a99f3f7d99c3e completed March 9, 2026, 8:56 a.m.
Created at: March 4, 2026, 7:50 p.m.