Triple

T14294436
Position Surface form Disambiguated ID Type / Status
Subject Shirley Ballas E354400 entity
Predicate spouse P13 FINISHED
Object Sammy Stopford
Sammy Stopford is a renowned British professional ballroom dancer and coach, particularly celebrated for his achievements in Latin dance.
E1091280 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: Sammy Stopford | Statement: [Shirley Ballas, spouse, Sammy Stopford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sammy Stopford
Context triple: [Shirley Ballas, spouse, Sammy Stopford]
  • A. Tim Souster
    Tim Souster was a British composer known for his work in contemporary classical and electronic music, including notable television scores.
  • B. Jack Steadman
    Jack Steadman is a British musician best known as the lead vocalist and primary songwriter of the indie rock band Bombay Bicycle Club.
  • C. Charlie Adlard
    Charlie Adlard is a British comic book artist best known as the long-running primary artist on Robert Kirkman’s series "The Walking Dead."
  • D. Noel Brailsford
    Noel Brailsford is an individual best known as the founder of the publication or organization named Tribune.
  • E. Ian Boldsworth
    Ian Boldsworth is a British comedian, writer, and podcaster best known for his work in alternative comedy and shows like the paranormal podcast "The ParaPod."
  • 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: Sammy Stopford
Triple: [Shirley Ballas, spouse, Sammy Stopford]
Generated description
Sammy Stopford is a renowned British professional ballroom dancer and coach, particularly celebrated for his achievements in Latin dance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sammy Stopford
Target entity description: Sammy Stopford is a renowned British professional ballroom dancer and coach, particularly celebrated for his achievements in Latin dance.
  • A. Tim Souster
    Tim Souster was a British composer known for his work in contemporary classical and electronic music, including notable television scores.
  • B. Jack Steadman
    Jack Steadman is a British musician best known as the lead vocalist and primary songwriter of the indie rock band Bombay Bicycle Club.
  • C. Charlie Adlard
    Charlie Adlard is a British comic book artist best known as the long-running primary artist on Robert Kirkman’s series "The Walking Dead."
  • D. Noel Brailsford
    Noel Brailsford is an individual best known as the founder of the publication or organization named Tribune.
  • E. Ian Boldsworth
    Ian Boldsworth is a British comedian, writer, and podcaster best known for his work in alternative comedy and shows like the paranormal podcast "The ParaPod."
  • 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_69d8278e17088190b328c5a9d4be74ff completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de717b35ec81908968994e65737c66 completed April 14, 2026, 4:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d2281d481909714f8d8cfe71514 completed May 8, 2026, 1:32 a.m.
NEDg Description generation batch_69fd3ded77748190b35908e046ccce67 completed May 8, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69fd3e7425348190abf09c103cc17305 completed May 8, 2026, 1:37 a.m.
Created at: April 10, 2026, 1:11 a.m.