Triple

T14053405
Position Surface form Disambiguated ID Type / Status
Subject The Atomic Kid E338149 entity
Predicate producer P490 FINISHED
Object Maurice Duke
Maurice Duke was a mid-20th-century American film producer known for working on Hollywood features such as the comedy "The Atomic Kid."
E1078847 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: Maurice Duke | Statement: [The Atomic Kid, producer, Maurice Duke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maurice Duke
Context triple: [The Atomic Kid, producer, Maurice Duke]
  • A. Maurice McEndree
    Maurice McEndree is a cinematographer known for his work on the film "Faces."
  • B. Maurice McEndree
    Maurice McEndree is a music producer best known for his work on the track "Shadows."
  • C. Maurice Ransford
    Maurice Ransford was a film art director known for his work on mid-20th-century Hollywood productions, including Westerns.
  • D. Maurice Monroe
    Maurice Monroe is a fictional character played by Don Cheadle, best known as a charismatic and morally ambiguous figure in the television series "House of Lies."
  • E. Maurice Monroe
    Maurice Monroe is a central character in the dark comedy series "Black Monday," portrayed as an ambitious, fast-talking Wall Street trader navigating the excesses and chaos of 1980s finance.
  • 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: Maurice Duke
Triple: [The Atomic Kid, producer, Maurice Duke]
Generated description
Maurice Duke was a mid-20th-century American film producer known for working on Hollywood features such as the comedy "The Atomic Kid."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maurice Duke
Target entity description: Maurice Duke was a mid-20th-century American film producer known for working on Hollywood features such as the comedy "The Atomic Kid."
  • A. Maurice McEndree
    Maurice McEndree is a cinematographer known for his work on the film "Faces."
  • B. Maurice McEndree
    Maurice McEndree is a music producer best known for his work on the track "Shadows."
  • C. Maurice Ransford
    Maurice Ransford was a film art director known for his work on mid-20th-century Hollywood productions, including Westerns.
  • D. Maurice Monroe
    Maurice Monroe is a fictional character played by Don Cheadle, best known as a charismatic and morally ambiguous figure in the television series "House of Lies."
  • E. Maurice Monroe
    Maurice Monroe is a central character in the dark comedy series "Black Monday," portrayed as an ambitious, fast-talking Wall Street trader navigating the excesses and chaos of 1980s finance.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de3c8bc54c8190a12f0fc056568538 completed April 14, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb65e63b48190bd5bd4a36cd15396 completed May 7, 2026, 3:57 p.m.
NEDg Description generation batch_69fcc76f99808190945fd3621fc183ff completed May 7, 2026, 5:10 p.m.
NED2 Entity disambiguation (via description) batch_69fcc807cdc48190a3b9dd940d17dc83 completed May 7, 2026, 5:12 p.m.
Created at: April 9, 2026, 10:20 p.m.