Triple

T21134607
Position Surface form Disambiguated ID Type / Status
Subject Earl Hindman E520782 entity
Predicate employer P7 FINISHED
Object ABC
ABC is a major American television network known for broadcasting a wide range of popular news, entertainment, and sports programming.
 E3937 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: ABC | Statement: [Earl Hindman, employer, ABC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ABC
Context triple: [Earl Hindman, employer, ABC]
  • A. ABC
    ABC is the abbreviation commonly used for the Associated British Corporation, a former British television company.
  • B. ABC
    ABC is the commonly used abbreviation for the Brazilian Academy of Sciences, a leading scientific society that promotes research and scientific development in Brazil.
  • C. ABC
    ABC is the IATA airport code for Albacete Air Base, a military airfield located near Albacete in Spain.
  • D. ABC
    ABC is the stock ticker symbol for Abcam, a global life sciences company specializing in research antibodies, reagents, and related tools.
  • E. ABC
    ABC is Australia's national public broadcaster, providing television, radio, and online services across the country.
  • 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: ABC
Triple: [Earl Hindman, employer, ABC]
Generated description
ABC is a major American television network known for broadcasting a wide range of popular news, entertainment, and sports programming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ABC
Target entity description: ABC is a major American television network known for broadcasting a wide range of popular news, entertainment, and sports programming.
  • A. ABC chosen
    ABC is a major American broadcast television network known for airing a wide range of national programming, including sports championships, news, and entertainment shows.
  • B. ABC
    ABC is Australia's national public broadcaster, providing television, radio, and online services across the country.
  • C. ABC
    ABC is the abbreviation commonly used for the Associated British Corporation, a former British television company.
  • D. ABC
    ABC is the common abbreviation for Asahi Broadcasting Corporation, a major Japanese television and radio broadcasting company based in Osaka.
  • E. ABC
    ABC is the stock ticker symbol for Abcam, a global life sciences company specializing in research antibodies, reagents, and related tools.
  • 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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e723592fd48190ba5977a1b229d51e completed April 21, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0965e5b04c8190addaa49cb9f6ad06 completed May 17, 2026, 6:53 a.m.
NEDg Description generation batch_6a0969cd36b081909e24ab92c0b2ab0a completed May 17, 2026, 7:10 a.m.
NED2 Entity disambiguation (via description) batch_6a096b373290819082f45e68772a81e4 completed May 17, 2026, 7:16 a.m.
Created at: April 16, 2026, 2:56 p.m.