Triple

T597778
Position Surface form Disambiguated ID Type / Status
Subject Horrible Bosses E11424 entity
Predicate producer P490 FINISHED
Object John Cheng
John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
E75268 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: John Cheng | Statement: [Horrible Bosses, producer, John Cheng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Cheng
Context triple: [Horrible Bosses, producer, John Cheng]
  • A. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • B. Yu-Chi Ho
    Yu-Chi Ho is a prominent control theorist and engineer known for his pioneering contributions to optimal control, dynamic systems, and game theory.
  • C. Tony Wu
    Tony Wu is a member of the technical team at xAI, the artificial intelligence company founded by Elon Musk.
  • D. Greg Yang
    Greg Yang is a mathematician and AI researcher known for his work on the theoretical foundations of deep learning and his role at xAI.
  • E. Jason Wong
    Jason Wong is a British actor known for his roles in film and television, including his appearance in Guy Ritchie's crime-comedy series "The Gentlemen."
  • 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: John Cheng
Triple: [Horrible Bosses, producer, John Cheng]
Generated description
John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Cheng
Target entity description: John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • A. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • B. Yu-Chi Ho
    Yu-Chi Ho is a prominent control theorist and engineer known for his pioneering contributions to optimal control, dynamic systems, and game theory.
  • C. Tony Wu
    Tony Wu is a member of the technical team at xAI, the artificial intelligence company founded by Elon Musk.
  • D. Greg Yang
    Greg Yang is a mathematician and AI researcher known for his work on the theoretical foundations of deep learning and his role at xAI.
  • E. Jason Wong
    Jason Wong is a British actor known for his roles in film and television, including his appearance in Guy Ritchie's crime-comedy series "The Gentlemen."
  • 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_69a4932779b881908688590d59c71900 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49d2b98d08190a1c1e8659efdfd75 completed March 1, 2026, 8:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5216e11248190a8c564a482d649a6 completed March 2, 2026, 5:34 a.m.
NEDg Description generation batch_69a521ce19e08190aadeb913977c2d2e completed March 2, 2026, 5:36 a.m.
NED2 Entity disambiguation (via description) batch_69a5226144f881908e0d1add6be6e156 completed March 2, 2026, 5:38 a.m.
Created at: March 1, 2026, 7:35 p.m.