Triple

T17172112
Position Surface form Disambiguated ID Type / Status
Subject So Fresh, So Clean E416759 entity
Predicate writer P1360 FINISHED
Object John Kelleher
John Kelleher is a writer best known for his work on the song "So Fresh, So Clean."
 E1371930 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 Kelleher | Statement: [So Fresh, So Clean, writer, John Kelleher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Kelleher
Context triple: [So Fresh, So Clean, writer, John Kelleher]
  • A. John Doherty
    John Doherty is known as the husband of American actress Michael Learned, famed for her role as Olivia Walton on the television series "The Waltons."
  • B. Joe Keenan
    Joe Keenan is an American television writer, producer, and novelist best known for his work on the sitcom "Frasier" and other acclaimed comedy projects.
  • C. Brian Kavanagh
    Brian Kavanagh is a film editor best known for his work on notable Australian and international films, including the drama "The Devil's Playground."
  • D. John Heffernan
    John Heffernan is a screenwriter best known for co-writing the cult action-thriller film "Snakes on a Plane."
  • E. John Heffernan
    John Heffernan is a British actor known for his work in television, film, and theatre, including prominent roles in political dramas and period pieces.
  • 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 Kelleher
Triple: [So Fresh, So Clean, writer, John Kelleher]
Generated description
John Kelleher is a writer best known for his work on the song "So Fresh, So Clean."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John Kelleher
Target entity description: John Kelleher is a writer best known for his work on the song "So Fresh, So Clean."
  • A. John Doherty
    John Doherty is known as the husband of American actress Michael Learned, famed for her role as Olivia Walton on the television series "The Waltons."
  • B. Joe Keenan
    Joe Keenan is an American television writer, producer, and novelist best known for his work on the sitcom "Frasier" and other acclaimed comedy projects.
  • C. Brian Kavanagh
    Brian Kavanagh is a film editor best known for his work on notable Australian and international films, including the drama "The Devil's Playground."
  • D. John Heffernan
    John Heffernan is a screenwriter best known for co-writing the cult action-thriller film "Snakes on a Plane."
  • E. John Heffernan
    John Heffernan is a British actor known for his work in television, film, and theatre, including prominent roles in political dramas and period pieces.
  • 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_69d886d5f34c8190b24564dfaa63f3fb completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3fc0ac22481909e992bb3a6ba36ad completed April 18, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0723ef338c819084b9f2d04aea4290 completed May 15, 2026, 1:47 p.m.
NEDg Description generation batch_6a07256bcabc819090f9a13046df763f completed May 15, 2026, 1:53 p.m.
NED2 Entity disambiguation (via description) batch_6a0726306be48190962cb5eebb214136 completed May 15, 2026, 1:57 p.m.
Created at: April 10, 2026, 5:37 a.m.