Triple

T16510120
Position Surface form Disambiguated ID Type / Status
Subject Concourse H E401037 entity
Predicate connectedTo P37 FINISHED
Object Terminal 3 main hall 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 main hall | Statement: [Concourse H, connectedTo, Terminal 3 main hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 3 main hall
Context triple: [Concourse H, connectedTo, Terminal 3 main hall]
  • A. Terminal 3A
    Terminal 3A is a major passenger terminal at Chongqing Jiangbei International Airport, designed to handle large volumes of domestic and international air traffic.
  • B. Terminal 3
    Terminal 3 is a major domestic passenger terminal at San Francisco International Airport, primarily serving United Airlines and its partners.
  • C. Terminal 3
    Terminal 3 is one of the passenger terminals at Adolfo Suárez Madrid–Barajas Airport in Madrid, Spain, serving as part of the airport’s main complex for domestic and international flights.
  • D. Terminal 3
    Terminal 3 is a major passenger terminal facility at Guangzhou Baiyun International Airport, serving as one of its primary hubs for domestic and international air travel.
  • E. Terminal 3
    Terminal 3 is a major new passenger terminal under development at Taiwan Taoyuan International Airport, intended to expand capacity and modernize the airport’s 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e54f7508190804bbae4c9bc8fe3 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067a31c8881909b05c49c8006785d completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 5:14 a.m.