Triple

T5197578
Position Surface form Disambiguated ID Type / Status
Subject Concourse A E117309 entity
Predicate connectedTo P37 FINISHED
Object Terminal 3 unclear NED1 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: Terminal 3 | Statement: [Concourse A, connectedTo, Terminal 3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 3
Context triple: [Concourse A, connectedTo, Terminal 3]
  • A. Terminal 3
    Terminal 3 is one of the main passenger terminals at Phoenix Sky Harbor International Airport, serving as a hub for multiple domestic and some international flights with modernized facilities and amenities.
  • B. Terminal 3
    Terminal 3 is the main international passenger terminal at José Martí International Airport in Havana, Cuba, handling most long-haul and major airline operations.
  • C. Terminal 3
    Terminal 3 is one of the main passenger terminals at Fort Lauderdale–Hollywood International Airport, serving various domestic and international airline operations.
  • D. Terminal 3
    Terminal 3 is one of the main domestic passenger terminals at Melbourne Airport, serving several Australian airlines and routes.
  • E. Terminal 3
    Terminal 3 is one of the passenger terminals at Manchester Airport, serving a range of domestic and international flights with dedicated check-in, security, and boarding facilities.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69bd4462ed04819084fcb01eb9d2fa74 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a1dbf7881909ed596ffdd1219bb completed March 20, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee09d84f08190b8270394fc35e195 completed March 21, 2026, 6:17 p.m.
Created at: March 20, 2026, 1:46 p.m.