Triple

T2594420
Position Surface form Disambiguated ID Type / Status
Subject Evander Holyfield vs. George Foreman E58194 entity
Predicate broadcaster P833 FINISHED
Object TVKO
TVKO was a pay-per-view television network and boxing broadcast brand operated by HBO that specialized in airing major prizefights and premium sports events.
 E281677 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: TVKO | Statement: [Evander Holyfield vs. George Foreman, broadcaster, TVKO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TVKO
Context triple: [Evander Holyfield vs. George Foreman, broadcaster, TVKO]
  • A. TK
    TK is the two-letter IATA airline designator used to identify Turkish Airlines in global aviation systems.
  • B. Tek
    Tek is a brand associated with Tektronix, known for electronic test and measurement equipment such as oscilloscopes and signal analyzers.
  • C. Tok
    Tok is a small unincorporated community in eastern Alaska, known as a gateway to the state for travelers on the Alaska Highway.
  • D. TKM
    TKM is the three-letter ISO 3166-1 alpha-3 country code assigned to Turkmenistan.
  • E. TVPA
    TVPA is the commonly used abbreviation for the Trafficking Victims Protection Act, a key U.S. federal law aimed at preventing human trafficking, protecting victims, and prosecuting traffickers.
  • 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: TVKO
Triple: [Evander Holyfield vs. George Foreman, broadcaster, TVKO]
Generated description
TVKO was a pay-per-view television network and boxing broadcast brand operated by HBO that specialized in airing major prizefights and premium sports events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TVKO
Target entity description: TVKO was a pay-per-view television network and boxing broadcast brand operated by HBO that specialized in airing major prizefights and premium sports events.
  • A. TK
    TK is the two-letter IATA airline designator used to identify Turkish Airlines in global aviation systems.
  • B. Tek
    Tek is a brand associated with Tektronix, known for electronic test and measurement equipment such as oscilloscopes and signal analyzers.
  • C. Tok
    Tok is a small unincorporated community in eastern Alaska, known as a gateway to the state for travelers on the Alaska Highway.
  • D. TKM
    TKM is the three-letter ISO 3166-1 alpha-3 country code assigned to Turkmenistan.
  • E. TVPA
    TVPA is the commonly used abbreviation for the Trafficking Victims Protection Act, a key U.S. federal law aimed at preventing human trafficking, protecting victims, and prosecuting traffickers.
  • 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_69ab4ac14040819098b13f4a27d5c8ff completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd427f58c8190af1c1a9724158c96 completed March 7, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69af83c3607c81908bb4aceca46c5392 completed March 10, 2026, 2:36 a.m.
NEDg Description generation batch_69af84a08ffc8190b113d07f3d322d0c completed March 10, 2026, 2:40 a.m.
NED2 Entity disambiguation (via description) batch_69af85a052448190898ee1a2f8368122 completed March 10, 2026, 2:44 a.m.
Created at: March 6, 2026, 9:49 p.m.