Triple

T2888190
Position Surface form Disambiguated ID Type / Status
Subject Wotif Group E59556 entity
Predicate brand P1500 FINISHED
Object Travel.com.au
Travel.com.au is an Australian online travel agency brand offering services such as flight, hotel, and holiday package bookings.
E306721 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: Travel.com.au | Statement: [Wotif Group, brand, Travel.com.au]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Travel.com.au
Context triple: [Wotif Group, brand, Travel.com.au]
  • A. Avalon Travel
    Avalon Travel is a publishing imprint best known for producing travel guides and related travel literature.
  • B. trivago
    trivago is a global hotel and accommodation metasearch platform that compares prices from numerous booking sites to help users find and book lodging deals.
  • C. Qantas Holidays
    Qantas Holidays is the tour and holiday packaging arm of Qantas, offering flights bundled with accommodation, tours, and other travel services.
  • D. Booking.com
    Booking.com is a major global online travel agency that allows users to search for and book accommodations such as hotels, apartments, and vacation rentals.
  • E. Wotif Group
    Wotif Group is an online travel company best known for its hotel and accommodation booking platforms, particularly in the Australian and Asia-Pacific markets.
  • 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: Travel.com.au
Triple: [Wotif Group, brand, Travel.com.au]
Generated description
Travel.com.au is an Australian online travel agency brand offering services such as flight, hotel, and holiday package bookings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Travel.com.au
Target entity description: Travel.com.au is an Australian online travel agency brand offering services such as flight, hotel, and holiday package bookings.
  • A. Avalon Travel
    Avalon Travel is a publishing imprint best known for producing travel guides and related travel literature.
  • B. trivago
    trivago is a global hotel and accommodation metasearch platform that compares prices from numerous booking sites to help users find and book lodging deals.
  • C. Qantas Holidays
    Qantas Holidays is the tour and holiday packaging arm of Qantas, offering flights bundled with accommodation, tours, and other travel services.
  • D. Booking.com
    Booking.com is a major global online travel agency that allows users to search for and book accommodations such as hotels, apartments, and vacation rentals.
  • E. Wotif Group
    Wotif Group is an online travel company best known for its hotel and accommodation booking platforms, particularly in the Australian and Asia-Pacific markets.
  • 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_69ab4ac739188190a112f42a5a69c951 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abe04918908190aad08defd1b26d97 completed March 7, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69b0317601688190a8a99644579b137c completed March 10, 2026, 2:57 p.m.
NEDg Description generation batch_69b032aa567081909402532d6fe438bc completed March 10, 2026, 3:03 p.m.
NED2 Entity disambiguation (via description) batch_69b033db495c8190bb6989210d72307b completed March 10, 2026, 3:08 p.m.
Created at: March 6, 2026, 10:03 p.m.