Triple

T10493119
Position Surface form Disambiguated ID Type / Status
Subject Dead Ringer E247466 entity
Predicate producer P490 FINISHED
Object Robert Brandt
Robert Brandt is a film producer known for his work on the movie "Dead Ringer."
E868809 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: Robert Brandt | Statement: [Dead Ringer, producer, Robert Brandt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Brandt
Context triple: [Dead Ringer, producer, Robert Brandt]
  • A. Robert Brandt
    Robert Brandt was the husband of American actress Janet Leigh, known primarily for his marriage to the famed Hollywood star.
  • B. Ben Braun
    Ben Braun is an American college basketball coach best known for revitalizing the University of California, Berkeley men's basketball program in the late 1990s and early 2000s.
  • C. Charles Brandt
    Charles Brandt is an American author and former investigator best known for writing the true-crime book "I Heard You Paint Houses," which inspired the film "The Irishman."
  • D. Paul Biegler
    Paul Biegler is a small-town Michigan lawyer and the central protagonist of the courtroom drama novel and film "Anatomy of a Murder."
  • E. Hans Bradtke
    Hans Bradtke was a German lyricist best known for writing popular song texts in the mid-20th century, including adaptations of international hits.
  • 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: Robert Brandt
Triple: [Dead Ringer, producer, Robert Brandt]
Generated description
Robert Brandt is a film producer known for his work on the movie "Dead Ringer."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robert Brandt
Target entity description: Robert Brandt is a film producer known for his work on the movie "Dead Ringer."
  • A. Robert Brandt
    Robert Brandt was the husband of American actress Janet Leigh, known primarily for his marriage to the famed Hollywood star.
  • B. Ben Braun
    Ben Braun is an American college basketball coach best known for revitalizing the University of California, Berkeley men's basketball program in the late 1990s and early 2000s.
  • C. Charles Brandt
    Charles Brandt is an American author and former investigator best known for writing the true-crime book "I Heard You Paint Houses," which inspired the film "The Irishman."
  • D. Paul Biegler
    Paul Biegler is a small-town Michigan lawyer and the central protagonist of the courtroom drama novel and film "Anatomy of a Murder."
  • E. Hans Bradtke
    Hans Bradtke was a German lyricist best known for writing popular song texts in the mid-20th century, including adaptations of international hits.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5097ecbec8190807c4fcc85662026 completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90dd040f48190a645ebd131f9205c completed April 10, 2026, 2:48 p.m.
NEDg Description generation batch_69d911dd4198819089585462af6b5ef5 completed April 10, 2026, 3:06 p.m.
NED2 Entity disambiguation (via description) batch_69d9126254408190a79ea571649416f6 completed April 10, 2026, 3:08 p.m.
Created at: April 6, 2026, 12:24 p.m.