Triple

T2668170
Position Surface form Disambiguated ID Type / Status
Subject Mark Robson E55686 entity
Predicate notableWork P4 FINISHED
Object Champion
"Champion" is a 1949 American film noir boxing drama directed by Mark Robson and starring Kirk Douglas as an ambitious but ruthless prizefighter.
 E288355 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: Champion | Statement: [Mark Robson, notableWork, Champion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Champion
Context triple: [Mark Robson, notableWork, Champion]
  • A. Champ
    Champ is the Dallas Mavericks’ horse-themed team mascot known for energizing crowds at their NBA games.
  • B. Champ
    Champ is a supporting character in the action-spy film "Kingsman: The Golden Circle," serving as a high-ranking member of the American Statesman organization.
  • C. The Champion of the World
    "The Champion of the World" is a film featuring Russian actress Svetlana Khodchenkova in a prominent role.
  • D. City of Champions
    City of Champions is the nickname of Brockton, Massachusetts, known for its rich boxing history and producing legendary fighters like Rocky Marciano and Marvin Hagler.
  • E. City of Champions
    City of Champions is the nickname of Duncanville, Texas, highlighting its strong tradition of success in high school athletics and other competitive activities.
  • 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: Champion
Triple: [Mark Robson, notableWork, Champion]
Generated description
"Champion" is a 1949 American film noir boxing drama directed by Mark Robson and starring Kirk Douglas as an ambitious but ruthless prizefighter.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Champion
Target entity description: "Champion" is a 1949 American film noir boxing drama directed by Mark Robson and starring Kirk Douglas as an ambitious but ruthless prizefighter.
  • A. Champ
    Champ is the Dallas Mavericks’ horse-themed team mascot known for energizing crowds at their NBA games.
  • B. Champ
    Champ is a supporting character in the action-spy film "Kingsman: The Golden Circle," serving as a high-ranking member of the American Statesman organization.
  • C. The Champion of the World
    "The Champion of the World" is a film featuring Russian actress Svetlana Khodchenkova in a prominent role.
  • D. City of Champions
    City of Champions is the nickname of Brockton, Massachusetts, known for its rich boxing history and producing legendary fighters like Rocky Marciano and Marvin Hagler.
  • E. City of Champions
    City of Champions is the nickname of Duncanville, Texas, highlighting its strong tradition of success in high school athletics and other competitive activities.
  • 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_69ab49e54de48190be708cd1cf8be073 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd98a4ee88190aa7ef914e316ba31 completed March 7, 2026, 7:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa05b008881908049751b73e800d0 completed March 10, 2026, 4:38 a.m.
NEDg Description generation batch_69afa21322248190bd472fc7578840fe completed March 10, 2026, 4:46 a.m.
NED2 Entity disambiguation (via description) batch_69afa286c218819084a525556cb7b3e3 completed March 10, 2026, 4:48 a.m.
Created at: March 6, 2026, 9:54 p.m.