Triple

T13993716
Position Surface form Disambiguated ID Type / Status
Subject Back to Black E336642 entity
Predicate producer P490 FINISHED
Object Tom Elmhirst
Tom Elmhirst is a Grammy-winning British mix engineer and producer known for his work with artists such as Amy Winehouse, Adele, and David Bowie.
 E1072883 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: Tom Elmhirst | Statement: [Back to Black, producer, Tom Elmhirst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom Elmhirst
Context triple: [Back to Black, producer, Tom Elmhirst]
  • A. Sam Pilling
    Sam Pilling is a British director known for his visually inventive and narrative-driven music videos for prominent contemporary artists.
  • B. Jonathan Gledhill
    Jonathan Gledhill was an English Anglican bishop who served in senior episcopal roles in the Church of England, including as Bishop of Stafford.
  • C. Tim Fywell
    Tim Fywell is a British film and television director known for his work on literary adaptations and period dramas.
  • D. Glyn Harman
    Glyn Harman is a British mathematician known for his contributions to analytic number theory, particularly in the study of prime numbers and Diophantine approximation.
  • E. Michael Harnett
    Michael Harnett is the birth name of Michael Hartnett, a prominent Irish poet known for his lyrical work in both English and Irish.
  • 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: Tom Elmhirst
Triple: [Back to Black, producer, Tom Elmhirst]
Generated description
Tom Elmhirst is a Grammy-winning British mix engineer and producer known for his work with artists such as Amy Winehouse, Adele, and David Bowie.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom Elmhirst
Target entity description: Tom Elmhirst is a Grammy-winning British mix engineer and producer known for his work with artists such as Amy Winehouse, Adele, and David Bowie.
  • A. Sam Pilling
    Sam Pilling is a British director known for his visually inventive and narrative-driven music videos for prominent contemporary artists.
  • B. Jonathan Gledhill
    Jonathan Gledhill was an English Anglican bishop who served in senior episcopal roles in the Church of England, including as Bishop of Stafford.
  • C. Tim Fywell
    Tim Fywell is a British film and television director known for his work on literary adaptations and period dramas.
  • D. Glyn Harman
    Glyn Harman is a British mathematician known for his contributions to analytic number theory, particularly in the study of prime numbers and Diophantine approximation.
  • E. Michael Harnett
    Michael Harnett is the birth name of Michael Hartnett, a prominent Irish poet known for his lyrical work in both English and Irish.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb3b5d881909f15a1e08bb202f3 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9a7e8c8190a0fd0cd67ff50741 completed May 6, 2026, 9:03 p.m.
NEDg Description generation batch_69fbad64934481908ad35366ded9c7a0 completed May 6, 2026, 9:06 p.m.
NED2 Entity disambiguation (via description) batch_69fbae1c5c988190bcc800d701bccca3 completed May 6, 2026, 9:09 p.m.
Created at: April 9, 2026, 10:19 p.m.