Triple

T19160150
Position Surface form Disambiguated ID Type / Status
Subject Ben Johnson E469029 entity
Predicate shirtName P744 FINISHED
Object Johnson
Johnson is the shirt name used by Canadian sprinter Ben Johnson, a former world-record holder in the 100 meters whose career was marred by a high-profile doping scandal.
E33363 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: Johnson | Statement: [Ben Johnson, shirtName, Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johnson
Context triple: [Ben Johnson, shirtName, Johnson]
  • A. Wilson
    Wilson is a small unincorporated community located in the U.S. state of Virginia.
  • B. Wilson
    Wilson is a fictional character from the Samba universe, known for his role within that setting’s stories.
  • C. Wilson
    "Wilson" is a 2017 American comedy-drama film, based on Daniel Clowes' graphic novel, about a lonely, neurotic middle-aged man who tries to reconnect with his ex-wife and the daughter he never knew.
  • D. John
    John is the given name of John Bardeen, the American physicist who uniquely won the Nobel Prize in Physics twice for his work on the transistor and superconductivity.
  • E. John
    John is the formal first name of Johnny Most, the famed American sports broadcaster known for his passionate radio commentary of Boston Celtics basketball games.
  • 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: Johnson
Triple: [Ben Johnson, shirtName, Johnson]
Generated description
Johnson is the shirt name used by Canadian sprinter Ben Johnson, a former world-record holder in the 100 meters whose career was marred by a high-profile doping scandal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Johnson
Target entity description: Johnson is the shirt name used by Canadian sprinter Ben Johnson, a former world-record holder in the 100 meters whose career was marred by a high-profile doping scandal.
  • A. Johnson chosen
    Johnson is a common English surname borne by numerous notable individuals across politics, arts, sports, and other fields.
  • B. Wilson
    Wilson is a small unincorporated community located in the U.S. state of Virginia.
  • C. Wilson
    Wilson is a fictional character from the Samba universe, known for his role within that setting’s stories.
  • D. Wilson
    "Wilson" is a 2017 American comedy-drama film, based on Daniel Clowes' graphic novel, about a lonely, neurotic middle-aged man who tries to reconnect with his ex-wife and the daughter he never knew.
  • E. John
    John is the given name of John Bardeen, the American physicist who uniquely won the Nobel Prize in Physics twice for his work on the transistor and superconductivity.
  • F. None of above.

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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eebc52dc819085666dbbeea365a6 completed April 20, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a06f25ad7448190b355a1bef148a09c completed May 15, 2026, 10:15 a.m.
NEDg Description generation batch_6a06f39537ac8190b8f38a123ac02556 completed May 15, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_6a06f4199a588190943d3d45536a228c completed May 15, 2026, 10:23 a.m.
Created at: April 10, 2026, 12:06 p.m.