Triple

T18634610
Position Surface form Disambiguated ID Type / Status
Subject American Gigolo E455510 entity
Predicate stars P1956 FINISHED
Object Tom Stewart
Tom Stewart is an actor known for his role in the film "American Gigolo."
E1334388 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: Tom Stewart | Statement: [American Gigolo, stars, Tom Stewart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Stewart
Context triple: [American Gigolo, stars, Tom Stewart]
  • A. Kevin Stevens
    Kevin Stevens is a former American NHL power forward best known for his high-scoring seasons with the Pittsburgh Penguins in the early 1990s.
  • B. Jim Stewart
    Jim Stewart was an American record producer and co-founder of the influential soul music label Stax Records in Memphis, Tennessee.
  • C. Jim Stewart
    Jim Stewart is a film editor known for his work on the animated feature "Monsters, Inc."
  • D. Ben Starr
    Ben Starr was an American television and film writer best known for his work on classic sitcoms and comedy scripts in the mid-20th century.
  • E. Bob Stewart
    Bob Stewart was an American television producer and game show creator best known for developing popular formats such as "The Price Is Right," "To Tell the Truth," and "Password."
  • 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: Tom Stewart
Triple: [American Gigolo, stars, Tom Stewart]
Generated description
Tom Stewart is an actor known for his role in the film "American Gigolo."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tom Stewart
Target entity description: Tom Stewart is an actor known for his role in the film "American Gigolo."
  • A. Kevin Stevens
    Kevin Stevens is a former American NHL power forward best known for his high-scoring seasons with the Pittsburgh Penguins in the early 1990s.
  • B. Jim Stewart
    Jim Stewart was an American record producer and co-founder of the influential soul music label Stax Records in Memphis, Tennessee.
  • C. Jim Stewart
    Jim Stewart is a film editor known for his work on the animated feature "Monsters, Inc."
  • D. Ben Starr
    Ben Starr was an American television and film writer best known for his work on classic sitcoms and comedy scripts in the mid-20th century.
  • E. Bob Stewart
    Bob Stewart was an American television producer and game show creator best known for developing popular formats such as "The Price Is Right," "To Tell the Truth," and "Password."
  • 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_69d8d38cc7948190a55ea64e5638994e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54fc80b308190932303231524d372 completed April 19, 2026, 9:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050d8039f481909ffe9d62afbb2a23 completed May 13, 2026, 11:47 p.m.
NEDg Description generation batch_6a050df74ca08190a7554396e052b702 completed May 13, 2026, 11:49 p.m.
NED2 Entity disambiguation (via description) batch_6a050ecc33e48190bc28430a6a771492 completed May 13, 2026, 11:52 p.m.
Created at: April 10, 2026, 11:46 a.m.