Triple

T11258156
Position Surface form Disambiguated ID Type / Status
Subject JNB E266492 entity
Predicate hasTerminal P182 FINISHED
Object Terminal A E266496 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 A | Statement: [JNB, hasTerminal, Terminal A]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal A
Context triple: [JNB, hasTerminal, Terminal A]
  • A. Terminal A
    Terminal A is one of the passenger terminals at Boston Logan International Airport, serving as a hub for several domestic and international airline operations.
  • B. Terminal A
    Terminal A is one of the main passenger terminals at Newark Liberty International Airport, serving as a hub for various domestic and regional airline operations.
  • C. Terminal A
    Terminal A is one of the passenger terminals at Hollywood Burbank Airport, serving as a primary facility for airline check-in, security screening, and boarding.
  • D. Terminal A
    Terminal A is a passenger terminal at Volgograd International Airport in Russia, serving as one of the airport’s main facilities for handling flights and travelers.
  • E. Terminal A chosen
    Terminal A is one of the main passenger terminals at O. R. Tambo International Airport in Johannesburg, serving as a key hub for airline check-in, departures, and arrivals.
  • 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_69d6aac7953c8190b82caf9d7640fdf9 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e935b85c819085e1abf2dd4099c5 completed April 9, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4ccada158819080e49833e09f84a0 completed April 19, 2026, 12:38 p.m.
Created at: April 8, 2026, 9:31 p.m.