Triple

T20898995
Position Surface form Disambiguated ID Type / Status
Subject Concourse E (SFO) E514617 entity
Predicate servesAirline P12356 FINISHED
Object United Express NE NERFINISHED

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: United Express | Statement: [Concourse E (SFO), servesAirline, United Express]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: United Express
Context triple: [Concourse E (SFO), servesAirline, United Express]
  • A. United Express chosen
    United Express is the regional brand for United Airlines, operating shorter-haul feeder flights to connect passengers to United’s mainline network.
  • B. US Airways Express
    US Airways Express was the regional brand under which several contracted airlines operated short-haul feeder flights for US Airways in the United States.
  • C. Airlink Express
    Airlink Express is a former dedicated airport bus service that connected Dublin Airport with central Dublin, operated by the city’s public transport company Dublin Bus.
  • D. Travelers Express
    Travelers Express was a financial services company that evolved into or was a predecessor of MoneyGram, helping establish its global money transfer business.
  • E. Shuttle America
    Shuttle America was a U.S. regional airline that operated feeder flights for major carriers under various brand agreements before ceasing operations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8f92bd88190b59b2131ad1d9aa1 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.