Triple

T2995088
Position Surface form Disambiguated ID Type / Status
Subject Howard Cosell E81046 entity
Predicate familyName P18 FINISHED
Object Cosell
Cosell is the surname of Howard Cosell, the influential and outspoken American sports journalist and broadcaster best known for his work on Monday Night Football.
 E315690 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: Cosell | Statement: [Howard Cosell, familyName, Cosell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cosell
Context triple: [Howard Cosell, familyName, Cosell]
  • A. Daboll
    Daboll is a surname most prominently associated with Brian Daboll, a professional American football coach in the National Football League.
  • B. Cosmo Brown
    Cosmo Brown is the wisecracking, musically gifted best friend and sidekick to Don Lockwood in the classic Hollywood musical film "Singin' in the Rain."
  • C. Bryc
    Bryc is an alternative spelling of the given name Bryce, typically used as a modern or stylistic variant.
  • D. Keeler
    Keeler is a surname most notably associated with James Edward Keeler, an American astronomer known for his pioneering work on Saturn's rings and spectroscopy.
  • E. Leo Gordon
    Leo Gordon was an American character actor and screenwriter known for his tough-guy roles in numerous Westerns and crime films from the 1950s through the 1970s.
  • 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: Cosell
Triple: [Howard Cosell, familyName, Cosell]
Generated description
Cosell is the surname of Howard Cosell, the influential and outspoken American sports journalist and broadcaster best known for his work on Monday Night Football.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cosell
Target entity description: Cosell is the surname of Howard Cosell, the influential and outspoken American sports journalist and broadcaster best known for his work on Monday Night Football.
  • A. Daboll
    Daboll is a surname most prominently associated with Brian Daboll, a professional American football coach in the National Football League.
  • B. Cosmo Brown
    Cosmo Brown is the wisecracking, musically gifted best friend and sidekick to Don Lockwood in the classic Hollywood musical film "Singin' in the Rain."
  • C. Bryc
    Bryc is an alternative spelling of the given name Bryce, typically used as a modern or stylistic variant.
  • D. Keeler
    Keeler is a surname most notably associated with James Edward Keeler, an American astronomer known for his pioneering work on Saturn's rings and spectroscopy.
  • E. Leo Gordon
    Leo Gordon was an American character actor and screenwriter known for his tough-guy roles in numerous Westerns and crime films from the 1950s through the 1970s.
  • 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_69ad8b187fc8819085914d3c9ea3142d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99f2e5888190b3346012e2578dab completed March 8, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b10908cfe48190bf244d5a3dbc958b completed March 11, 2026, 6:17 a.m.
NEDg Description generation batch_69b10ab5e3488190b2d8c98dd296cbe5 completed March 11, 2026, 6:24 a.m.
NED2 Entity disambiguation (via description) batch_69b10b1664f081909b521ee8dd5954f9 completed March 11, 2026, 6:26 a.m.
Created at: March 8, 2026, 2:59 p.m.