Triple

T492880
Position Surface form Disambiguated ID Type / Status
Subject Creed (film) E10226 entity
Predicate writer P1360 FINISHED
Object Aaron Covington
Aaron Covington is an American screenwriter best known for co-writing the boxing drama film "Creed."
 E72651 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: Aaron Covington | Statement: [Creed (film), writer, Aaron Covington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Aaron Covington
Context triple: [Creed (film), writer, Aaron Covington]
  • A. Jason Hudson
    Jason Hudson was the brother of singer and actress Jennifer Hudson, tragically murdered in a widely publicized 2008 family shooting in Chicago.
  • B. Austin Rivers
    Austin Rivers is an American professional basketball player known for his scoring ability and time in the NBA with multiple teams, including the Los Angeles Clippers and Houston Rockets.
  • C. Nate Rogers
    Nate Rogers is a notable individual who shares the Rogers surname and has achieved enough recognition to be specifically identified among its bearers.
  • D. Dylan Highsmith
    Dylan Highsmith is a film editor best known for his work on major action and science-fiction movies, including Pacific Rim: Uprising.
  • E. Aaron Courville
    Aaron Courville is a machine learning researcher and professor best known as a co-author of the influential deep learning textbook alongside Yoshua Bengio and Ian Goodfellow.
  • 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: Aaron Covington
Triple: [Creed (film), writer, Aaron Covington]
Generated description
Aaron Covington is an American screenwriter best known for co-writing the boxing drama film "Creed."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Aaron Covington
Target entity description: Aaron Covington is an American screenwriter best known for co-writing the boxing drama film "Creed."
  • A. Jason Hudson
    Jason Hudson was the brother of singer and actress Jennifer Hudson, tragically murdered in a widely publicized 2008 family shooting in Chicago.
  • B. Austin Rivers
    Austin Rivers is an American professional basketball player known for his scoring ability and time in the NBA with multiple teams, including the Los Angeles Clippers and Houston Rockets.
  • C. Nate Rogers
    Nate Rogers is a notable individual who shares the Rogers surname and has achieved enough recognition to be specifically identified among its bearers.
  • D. Dylan Highsmith
    Dylan Highsmith is a film editor best known for his work on major action and science-fiction movies, including Pacific Rim: Uprising.
  • E. Aaron Courville
    Aaron Courville is a machine learning researcher and professor best known as a co-author of the influential deep learning textbook alongside Yoshua Bengio and Ian Goodfellow.
  • 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_69a2e847df8481909239ec08ccf1e376 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f0faab4881909f65f172198b5bd2 completed Feb. 28, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5089817248190b53d78e5b937026b completed March 2, 2026, 3:48 a.m.
NEDg Description generation batch_69a5094d47b4819099e51ccfd8a14416 completed March 2, 2026, 3:51 a.m.
NED2 Entity disambiguation (via description) batch_69a5099a81988190941857838551b9c6 completed March 2, 2026, 3:52 a.m.
Created at: Feb. 28, 2026, 1:12 p.m.