Triple

T13961392
Position Surface form Disambiguated ID Type / Status
Subject Shine Group E335800 entity
Predicate hasSubsidiary P254 FINISHED
Object Shine TV
Shine TV is a British television production company known for creating and producing a range of popular factual and entertainment programming.
E1071669 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: Shine TV | Statement: [Shine Group, hasSubsidiary, Shine TV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shine TV
Context triple: [Shine Group, hasSubsidiary, Shine TV]
  • A. North One Television
    North One Television is a British television production company known for creating popular factual, entertainment, and sports programming for major UK broadcasters.
  • B. Star TV
    Star TV is a major Asian satellite television network known for its broad entertainment and news programming across multiple countries.
  • C. SBS Television
    SBS Television is an Australian free-to-air public broadcasting network known for its multicultural and multilingual programming.
  • D. Orange TV
    Orange TV is a subscription-based television platform operated by the telecommunications company Orange, offering a range of live channels and on-demand content.
  • E. Channel 5
    Channel 5 is a British free-to-air television network known for a mix of entertainment, documentaries, and imported programming.
  • 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: Shine TV
Triple: [Shine Group, hasSubsidiary, Shine TV]
Generated description
Shine TV is a British television production company known for creating and producing a range of popular factual and entertainment programming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shine TV
Target entity description: Shine TV is a British television production company known for creating and producing a range of popular factual and entertainment programming.
  • A. North One Television
    North One Television is a British television production company known for creating popular factual, entertainment, and sports programming for major UK broadcasters.
  • B. Star TV
    Star TV is a major Asian satellite television network known for its broad entertainment and news programming across multiple countries.
  • C. SBS Television
    SBS Television is an Australian free-to-air public broadcasting network known for its multicultural and multilingual programming.
  • D. Orange TV
    Orange TV is a subscription-based television platform operated by the telecommunications company Orange, offering a range of live channels and on-demand content.
  • E. Channel 5
    Channel 5 is a British free-to-air television network known for a mix of entertainment, documentaries, and imported programming.
  • 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_69d81c61f3508190aaf2ca0dc0002c59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e7c73d48190b8e02971b5a8ed5f completed April 14, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fba1d6b2e88190b4d2237413f509ee completed May 6, 2026, 8:17 p.m.
NEDg Description generation batch_69fba5eaf3a48190bc93c0fcb2723ef5 completed May 6, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_69fba71a91fc8190b24185994673b33b completed May 6, 2026, 8:39 p.m.
Created at: April 9, 2026, 10:18 p.m.