Triple

T14989577
Position Surface form Disambiguated ID Type / Status
Subject King Kong (2005 film score) E373796 entity
Predicate orchestrator P4735 FINISHED
Object John Kull
John Kull is a film music orchestrator known for his work on major Hollywood scores, including the 2005 remake of King Kong.
 E1131516 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: John Kull | Statement: [King Kong (2005 film score), orchestrator, John Kull]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Kull
Context triple: [King Kong (2005 film score), orchestrator, John Kull]
  • A. Ed Kull
    Ed Kull is a collegiate sports administrator who serves as the athletic director for Fordham University's Fordham Rams athletic programs.
  • B. Garth Craven
    Garth Craven is a film editor known for his work on major Hollywood productions, including the comedy sequel "Miss Congeniality 2: Armed and Fabulous."
  • C. Gunnar Scott
    Gunnar Scott is a fictional singer-songwriter and guitarist who serves as one of the central characters on the television drama series "Nashville."
  • D. Kurt Dussander
    Kurt Dussander is a former Nazi war criminal living under an assumed identity who becomes the sinister focus of Stephen King’s novella "Apt Pupil."
  • E. Conrad Kain
    Conrad Kain was an Austrian mountain guide and pioneering alpinist renowned for numerous first ascents in the Canadian Rockies and beyond.
  • 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: John Kull
Triple: [King Kong (2005 film score), orchestrator, John Kull]
Generated description
John Kull is a film music orchestrator known for his work on major Hollywood scores, including the 2005 remake of King Kong.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John Kull
Target entity description: John Kull is a film music orchestrator known for his work on major Hollywood scores, including the 2005 remake of King Kong.
  • A. Ed Kull
    Ed Kull is a collegiate sports administrator who serves as the athletic director for Fordham University's Fordham Rams athletic programs.
  • B. Garth Craven
    Garth Craven is a film editor known for his work on major Hollywood productions, including the comedy sequel "Miss Congeniality 2: Armed and Fabulous."
  • C. Gunnar Scott
    Gunnar Scott is a fictional singer-songwriter and guitarist who serves as one of the central characters on the television drama series "Nashville."
  • D. Kurt Dussander
    Kurt Dussander is a former Nazi war criminal living under an assumed identity who becomes the sinister focus of Stephen King’s novella "Apt Pupil."
  • E. Conrad Kain
    Conrad Kain was an Austrian mountain guide and pioneering alpinist renowned for numerous first ascents in the Canadian Rockies and beyond.
  • 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7148a308190a687f4d0d61397c6 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe969683348190bb4688f24227af88 completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe98a230948190b35e2883475cff33 completed May 9, 2026, 2:14 a.m.
NED2 Entity disambiguation (via description) batch_69fe993c6094819086f0de1743272fd4 completed May 9, 2026, 2:17 a.m.
Created at: April 10, 2026, 2:53 a.m.