Triple

T20708014
Position Surface form Disambiguated ID Type / Status
Subject Vy E508954 entity
Predicate hasSubsidiary P254 FINISHED
Object Vy Travel
Vy Travel is a Norwegian travel company within the Vy Group that operates and sells bus and other transport services.
E1445474 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: Vy Travel | Statement: [Vy, hasSubsidiary, Vy Travel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vy Travel
Context triple: [Vy, hasSubsidiary, Vy Travel]
  • A. Avalon Travel
    Avalon Travel is a publishing imprint best known for producing travel guides and related travel literature.
  • B. United Travel Getaway
    United Travel Getaway was a New Zealand television travel show known for showcasing holiday destinations and experiences to local audiences.
  • C. Coral Travel
    Coral Travel is a major international tour operator offering package holidays and travel services across popular leisure destinations.
  • D. Compass Travel
    Compass Travel is a regional bus operator in southern England providing local and interurban public transport services.
  • E. Morris Travel
    Morris Travel was a travel agency business that owned and operated Morris Air before the airline was acquired by Southwest Airlines.
  • 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: Vy Travel
Triple: [Vy, hasSubsidiary, Vy Travel]
Generated description
Vy Travel is a Norwegian travel company within the Vy Group that operates and sells bus and other transport services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Vy Travel
Target entity description: Vy Travel is a Norwegian travel company within the Vy Group that operates and sells bus and other transport services.
  • A. Avalon Travel
    Avalon Travel is a publishing imprint best known for producing travel guides and related travel literature.
  • B. United Travel Getaway
    United Travel Getaway was a New Zealand television travel show known for showcasing holiday destinations and experiences to local audiences.
  • C. Coral Travel
    Coral Travel is a major international tour operator offering package holidays and travel services across popular leisure destinations.
  • D. Compass Travel
    Compass Travel is a regional bus operator in southern England providing local and interurban public transport services.
  • E. Morris Travel
    Morris Travel was a travel agency business that owned and operated Morris Air before the airline was acquired by Southwest Airlines.
  • 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_69e0b4c40ad88190b81f77695366d328 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1952e888190877b79933970f7b0 completed April 21, 2026, 12:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7f4d5f08190a733c7247f51f492 completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08d8f47be881909859bbe23887d0fc completed May 16, 2026, 8:52 p.m.
NED2 Entity disambiguation (via description) batch_6a08d99214b48190b0ffba4026d3fa39 completed May 16, 2026, 8:54 p.m.
Created at: April 16, 2026, 12:14 p.m.