Triple

T1839887
Position Surface form Disambiguated ID Type / Status
Subject Kiss Me Deadly E41150 entity
Predicate starring P1507 FINISHED
Object Paul Stewart
Paul Stewart was an American character actor and director known for his tough-guy roles in film noir and classic Hollywood cinema.
E239864 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: Paul Stewart | Statement: [Kiss Me Deadly, starring, Paul Stewart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Stewart
Context triple: [Kiss Me Deadly, starring, Paul Stewart]
  • A. Tim Stevenson
    Tim Stevenson is a British public servant who has served as the ceremonial representative of the monarch in Oxfordshire.
  • B. Ken Ralston
    Ken Ralston is an acclaimed visual effects supervisor known for his groundbreaking work on major films such as the Star Wars and Back to the Future series.
  • C. Daniel Stewart
    Daniel Stewart was an American Revolutionary War officer and early Georgia politician and militia leader for whom Stewart County, Georgia, is named.
  • D. Don Stevens
    Don Stevens is a notable individual recognized for achievements significant enough to be distinguished from others sharing the surname Stevens.
  • E. Richard Stolley
    Richard Stolley was an influential American magazine editor best known for shaping modern celebrity journalism as the founding managing editor of People magazine.
  • 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: Paul Stewart
Triple: [Kiss Me Deadly, starring, Paul Stewart]
Generated description
Paul Stewart was an American character actor and director known for his tough-guy roles in film noir and classic Hollywood cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Paul Stewart
Target entity description: Paul Stewart was an American character actor and director known for his tough-guy roles in film noir and classic Hollywood cinema.
  • A. Tim Stevenson
    Tim Stevenson is a British public servant who has served as the ceremonial representative of the monarch in Oxfordshire.
  • B. Ken Ralston
    Ken Ralston is an acclaimed visual effects supervisor known for his groundbreaking work on major films such as the Star Wars and Back to the Future series.
  • C. Daniel Stewart
    Daniel Stewart was an American Revolutionary War officer and early Georgia politician and militia leader for whom Stewart County, Georgia, is named.
  • D. Don Stevens
    Don Stevens is a notable individual recognized for achievements significant enough to be distinguished from others sharing the surname Stevens.
  • E. Richard Stolley
    Richard Stolley was an influential American magazine editor best known for shaping modern celebrity journalism as the founding managing editor of People magazine.
  • 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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb03b3eb08190ae68d8476fc89c7f completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae58b4c9ac8190b9b54dc08f9440bf completed March 9, 2026, 5:20 a.m.
NEDg Description generation batch_69ae599c6b288190b7e173ffc505c605 completed March 9, 2026, 5:24 a.m.
NED2 Entity disambiguation (via description) batch_69ae5a42675c8190a019034e8a6bda21 completed March 9, 2026, 5:27 a.m.
Created at: March 4, 2026, 7:33 p.m.