Triple

T1227577
Position Surface form Disambiguated ID Type / Status
Subject Cinderella Man E26359 entity
Predicate portrays P264 FINISHED
Object Joe Gould
Joe Gould was the real-life boxing manager best known for guiding heavyweight champion James J. Braddock during his improbable rise in the 1930s.
E164464 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: Joe Gould | Statement: [Cinderella Man, portrays, Joe Gould]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Gould
Context triple: [Cinderella Man, portrays, Joe Gould]
  • A. George Merrill
    George Merrill is an American songwriter best known for co-writing Whitney Houston’s hit songs “How Will I Know” and “I Wanna Dance with Somebody (Who Loves Me).”
  • B. Don Brochu
    Don Brochu is a film editor best known for his work on major Hollywood movies, including the hit thriller "The Bodyguard."
  • C. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • D. Clay Benchley
    Clay Benchley is one of the children of Peter Benchley, the American author best known for writing the novel "Jaws."
  • E. Sidney Verba
    Sidney Verba was a prominent American political scientist renowned for his pioneering work on political participation, comparative politics, and civic culture.
  • 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: Joe Gould
Triple: [Cinderella Man, portrays, Joe Gould]
Generated description
Joe Gould was the real-life boxing manager best known for guiding heavyweight champion James J. Braddock during his improbable rise in the 1930s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Joe Gould
Target entity description: Joe Gould was the real-life boxing manager best known for guiding heavyweight champion James J. Braddock during his improbable rise in the 1930s.
  • A. George Merrill
    George Merrill is an American songwriter best known for co-writing Whitney Houston’s hit songs “How Will I Know” and “I Wanna Dance with Somebody (Who Loves Me).”
  • B. Don Brochu
    Don Brochu is a film editor best known for his work on major Hollywood movies, including the hit thriller "The Bodyguard."
  • C. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • D. Clay Benchley
    Clay Benchley is one of the children of Peter Benchley, the American author best known for writing the novel "Jaws."
  • E. Sidney Verba
    Sidney Verba was a prominent American political scientist renowned for his pioneering work on political participation, comparative politics, and civic culture.
  • 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be3b32a08190a36e96a3e51976eb completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad014954b08190a787d7e03e503d8d completed March 8, 2026, 4:55 a.m.
NEDg Description generation batch_69ad039c5d788190aa10636e2827b489 completed March 8, 2026, 5:05 a.m.
NED2 Entity disambiguation (via description) batch_69ad03fa7b0c8190906ed79f24723216 completed March 8, 2026, 5:07 a.m.
Created at: March 1, 2026, 7:47 p.m.