Triple

T1041862
Position Surface form Disambiguated ID Type / Status
Subject Inside the NBA E22485 entity
Predicate formerPanelist P858 FINISHED
Object Kevin Harlan
Kevin Harlan is an American sportscaster best known for his energetic play-by-play commentary on NBA and NFL broadcasts.
E124266 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: Kevin Harlan | Statement: [Inside the NBA, formerPanelist, Kevin Harlan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kevin Harlan
Context triple: [Inside the NBA, formerPanelist, Kevin Harlan]
  • A. Jed Harris
    Jed Harris was a prominent American theatrical producer and director known for staging influential Broadway productions in the mid-20th century.
  • B. Richard Stolley
    Richard Stolley was an influential American magazine editor best known for shaping modern celebrity journalism as the founding managing editor of People magazine.
  • C. Douglas Kirk
    Douglas Kirk is an individual notable enough to be recognized as a prominent bearer of the surname Kirk.
  • D. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • E. Michael V. Drake
    Michael V. Drake is an American academic leader and physician who has served as president of both The Ohio State University and the University of California system.
  • 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: Kevin Harlan
Triple: [Inside the NBA, formerPanelist, Kevin Harlan]
Generated description
Kevin Harlan is an American sportscaster best known for his energetic play-by-play commentary on NBA and NFL broadcasts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kevin Harlan
Target entity description: Kevin Harlan is an American sportscaster best known for his energetic play-by-play commentary on NBA and NFL broadcasts.
  • A. Jed Harris
    Jed Harris was a prominent American theatrical producer and director known for staging influential Broadway productions in the mid-20th century.
  • B. Richard Stolley
    Richard Stolley was an influential American magazine editor best known for shaping modern celebrity journalism as the founding managing editor of People magazine.
  • C. Douglas Kirk
    Douglas Kirk is an individual notable enough to be recognized as a prominent bearer of the surname Kirk.
  • D. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • E. Michael V. Drake
    Michael V. Drake is an American academic leader and physician who has served as president of both The Ohio State University and the University of California system.
  • 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_69a493d91478819094cc01fb65564bc1 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bb71e7f88190bf33bbe5ef2c68ff completed March 1, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac429ad45481908641fcaf72f7d1b9 completed March 7, 2026, 3:22 p.m.
NEDg Description generation batch_69ac4365965881909ff2cdf8eda07f91 completed March 7, 2026, 3:25 p.m.
NED2 Entity disambiguation (via description) batch_69ac43d1cd1c8190852f8811703ebd5f completed March 7, 2026, 3:27 p.m.
Created at: March 1, 2026, 7:42 p.m.