Triple

T3192962
Position Surface form Disambiguated ID Type / Status
Subject Bill Cowher E66865 entity
Predicate spouse P13 FINISHED
Object Kaye Cowher
Kaye Cowher was an American former professional basketball player and the wife of longtime Pittsburgh Steelers head coach Bill Cowher.
E335426 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: Kaye Cowher | Statement: [Bill Cowher, spouse, Kaye Cowher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaye Cowher
Context triple: [Bill Cowher, spouse, Kaye Cowher]
  • A. Leon Britton
    Leon Britton is an English former midfielder best known for his long, influential spell at Swansea City, where he helped guide the club from the lower leagues to the Premier League.
  • B. Michele Marsh
    Michele Marsh is an American actress best known for her role as Hodel in the 1971 film adaptation of the musical "Fiddler on the Roof."
  • C. Lynn Sykes
    Lynn Sykes is an American seismologist renowned for his pioneering work on plate tectonics and earthquake mechanisms.
  • D. Nicky Parsons
    Nicky Parsons is a former CIA logistics technician and ally of Jason Bourne in the Bourne film series, known for her insider knowledge of the agency’s covert operations.
  • E. Mo McRae
    Mo McRae is an American actor and producer known for his work in film and television, often appearing in crime dramas and action thrillers.
  • 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: Kaye Cowher
Triple: [Bill Cowher, spouse, Kaye Cowher]
Generated description
Kaye Cowher was an American former professional basketball player and the wife of longtime Pittsburgh Steelers head coach Bill Cowher.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kaye Cowher
Target entity description: Kaye Cowher was an American former professional basketball player and the wife of longtime Pittsburgh Steelers head coach Bill Cowher.
  • A. Leon Britton
    Leon Britton is an English former midfielder best known for his long, influential spell at Swansea City, where he helped guide the club from the lower leagues to the Premier League.
  • B. Michele Marsh
    Michele Marsh is an American actress best known for her role as Hodel in the 1971 film adaptation of the musical "Fiddler on the Roof."
  • C. Lynn Sykes
    Lynn Sykes is an American seismologist renowned for his pioneering work on plate tectonics and earthquake mechanisms.
  • D. Nicky Parsons
    Nicky Parsons is a former CIA logistics technician and ally of Jason Bourne in the Bourne film series, known for her insider knowledge of the agency’s covert operations.
  • E. Mo McRae
    Mo McRae is an American actor and producer known for his work in film and television, often appearing in crime dramas and action thrillers.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada713bf0c81908f3143f45f63a5ad completed March 8, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24ba8a8b48190824dac45e37217cc completed March 12, 2026, 5:14 a.m.
NEDg Description generation batch_69b24d13ef908190b7b54d653e4d1ea4 completed March 12, 2026, 5:20 a.m.
NED2 Entity disambiguation (via description) batch_69b24db9af3881909d3d89ad985356c6 completed March 12, 2026, 5:23 a.m.
Created at: March 8, 2026, 3:07 p.m.