Triple

T1549313
Position Surface form Disambiguated ID Type / Status
Subject Dara Khosrowshahi E33050 entity
Predicate employer P7 FINISHED
Object Expedia Group E7140 NE FINISHED

How this triple was built (2 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: Expedia Group | Statement: [Dara Khosrowshahi, employer, Expedia Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Expedia Group
Context triple: [Dara Khosrowshahi, employer, Expedia Group]
  • A. Expedia Group chosen
    Expedia Group is a leading American online travel and technology company that operates numerous global travel fare aggregators and travel metasearch engines.
  • B. 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.
  • C. Concur Technologies
    Concur Technologies is a software company best known for its cloud-based travel and expense management solutions used by businesses worldwide.
  • D. Sky Group
    Sky Group is a major European media and telecommunications conglomerate best known for its satellite television, broadband, and streaming services.
  • E. First Travel Corporation
    First Travel Corporation is a travel services company associated with entrepreneur and former baseball commissioner Peter Ueberroth.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a885ee6db8819099502bc5ce8af881 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90857bfb48190a2d66a601d228b72 completed March 5, 2026, 4:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad30a29ae88190ab1b2ca97b8ed09c completed March 8, 2026, 8:17 a.m.
Created at: March 4, 2026, 7:26 p.m.