Triple

T14805337
Position Surface form Disambiguated ID Type / Status
Subject Crash (2004 film) E348019 entity
Predicate producer P490 FINISHED
Object Mark R. Harris
Mark R. Harris is an American film producer best known for his work on the Academy Award–winning drama "Crash" (2004).
E1121300 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: Mark R. Harris | Statement: [Crash (2004 film), producer, Mark R. Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark R. Harris
Context triple: [Crash (2004 film), producer, Mark R. Harris]
  • A. Mark Harris
    Mark Harris is an actor known for his role in the British crime film "The Hatton Garden Job."
  • B. Mark Harris
    Mark Harris is an American entertainer and television personality best known as the much younger husband of comedian and actress Martha Raye and for his flamboyant appearances on talk shows in the 1990s.
  • C. Stephen Haise
    Stephen Haise is the son of American astronaut Fred Haise, one of the Apollo 13 crew members.
  • D. Thomas Edwin Ricks
    Thomas Edwin Ricks was a 19th-century Latter-day Saint pioneer and colonizer who played a key role in settling southeastern Idaho and founding what became Brigham Young University–Idaho.
  • E. Douglas Fackler
    Douglas Fackler is a bumbling, mild-mannered police cadet character from the "Police Academy" comedy film series.
  • 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: Mark R. Harris
Triple: [Crash (2004 film), producer, Mark R. Harris]
Generated description
Mark R. Harris is an American film producer best known for his work on the Academy Award–winning drama "Crash" (2004).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mark R. Harris
Target entity description: Mark R. Harris is an American film producer best known for his work on the Academy Award–winning drama "Crash" (2004).
  • A. Mark Harris
    Mark Harris is an actor known for his role in the British crime film "The Hatton Garden Job."
  • B. Mark Harris
    Mark Harris is an American entertainer and television personality best known as the much younger husband of comedian and actress Martha Raye and for his flamboyant appearances on talk shows in the 1990s.
  • C. Stephen Haise
    Stephen Haise is the son of American astronaut Fred Haise, one of the Apollo 13 crew members.
  • D. Thomas Edwin Ricks
    Thomas Edwin Ricks was a 19th-century Latter-day Saint pioneer and colonizer who played a key role in settling southeastern Idaho and founding what became Brigham Young University–Idaho.
  • E. Douglas Fackler
    Douglas Fackler is a bumbling, mild-mannered police cadet character from the "Police Academy" comedy film series.
  • 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_69d822ea8b7c819097dfadf3d45545e6 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decf32666081908e84f985c47eb963 completed April 14, 2026, 11:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24c6b3008190a0fac1dace40361a completed May 8, 2026, 6 p.m.
NEDg Description generation batch_69fe2d9c08d0819094d3affc082f4f8a completed May 8, 2026, 6:38 p.m.
NED2 Entity disambiguation (via description) batch_69fe2e0b3514819097f2d9d63cb6a143 completed May 8, 2026, 6:40 p.m.
Created at: April 10, 2026, 1:34 a.m.