Triple

T2834742
Position Surface form Disambiguated ID Type / Status
Subject Sarafina! E62321 entity
Predicate editedBy P1954 FINISHED
Object David Heitner
David Heitner is a film editor known for his work on the South African musical drama film "Sarafina!".
E302639 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: David Heitner | Statement: [Sarafina!, editedBy, David Heitner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Heitner
Context triple: [Sarafina!, editedBy, David Heitner]
  • A. Michael Kaplan
    Michael Kaplan is a composer and musician known for creating the music for the film "Burlesque."
  • B. Jeremy Shamos
    Jeremy Shamos is an American stage and screen actor known for his work on Broadway and in film and television.
  • C. Andrew G. Myers
    Andrew G. Myers is an American organic chemist renowned for his contributions to complex molecule synthesis and medicinal chemistry.
  • D. Jon Oberheide
    Jon Oberheide is a cybersecurity entrepreneur and researcher best known as the co-founder and former CTO of Duo Security, a leading multi-factor authentication and zero-trust security company.
  • E. Matthew C. Brown
    Matthew C. Brown is a film producer known for his work on the horror movie "Spectral."
  • 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: David Heitner
Triple: [Sarafina!, editedBy, David Heitner]
Generated description
David Heitner is a film editor known for his work on the South African musical drama film "Sarafina!".
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Heitner
Target entity description: David Heitner is a film editor known for his work on the South African musical drama film "Sarafina!".
  • A. Michael Kaplan
    Michael Kaplan is a composer and musician known for creating the music for the film "Burlesque."
  • B. Jeremy Shamos
    Jeremy Shamos is an American stage and screen actor known for his work on Broadway and in film and television.
  • C. Andrew G. Myers
    Andrew G. Myers is an American organic chemist renowned for his contributions to complex molecule synthesis and medicinal chemistry.
  • D. Jon Oberheide
    Jon Oberheide is a cybersecurity entrepreneur and researcher best known as the co-founder and former CTO of Duo Security, a leading multi-factor authentication and zero-trust security company.
  • E. Matthew C. Brown
    Matthew C. Brown is a film producer known for his work on the horror movie "Spectral."
  • 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_69ab4c3c39188190955b9c49d98463d8 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdec18b808190aedae2ed11d53b15 completed March 7, 2026, 8:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69afe8c45c548190ac67b94a845cc730 completed March 10, 2026, 9:47 a.m.
NEDg Description generation batch_69afe9a000c4819085be1794bff0d506 completed March 10, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_69b0010b0ddc8190b4bfb18448f88077 completed March 10, 2026, 11:31 a.m.
Created at: March 6, 2026, 10:01 p.m.