Triple

T23013278
Position Surface form Disambiguated ID Type / Status
Subject Firestone Grand Prix of St. Petersburg E572962 entity
Predicate usesAirportRunway P77854 FINISHED
Object Albert Whitted Airport runway LITERAL 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: Albert Whitted Airport runway | Statement: [Firestone Grand Prix of St. Petersburg, usesAirportRunway, Albert Whitted Airport runway]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usesAirportRunway
Context triple: [Firestone Grand Prix of St. Petersburg, usesAirportRunway, Albert Whitted Airport runway]
  • A. runwayUsage chosen
    Indicates that a particular runway is being used or assigned for aircraft operations such as takeoffs or landings.
  • B. isPrimaryRunwayOf
    Indicates that a runway serves as the main or principal runway for a particular airport or airfield.
  • C. runwayInformationAvailableIn
    Indicates that information about a runway is available within or through a specified medium, source, or context.
  • D. runwayCharacteristic
    Indicates a relationship where specific attributes or features are associated with a runway.
  • E. runwayAdjacentTo
    Indicates that a runway is directly next to or alongside another feature or area, with no significant separation between them.
  • F. None of above.

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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e300008190bb12c6388a8b3280 completed April 29, 2026, 4:06 a.m.
PD Predicate disambiguation batch_69ef3b9cd5488190bcd23183179f48cd completed April 27, 2026, 10:34 a.m.
Created at: April 17, 2026, 3:51 p.m.