Triple

T22230940
Position Surface form Disambiguated ID Type / Status
Subject Ratmalana E549463 entity
Predicate airportFormerRole P4950 FINISHED
Object main international airport of Sri Lanka (historical) 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: main international airport of Sri Lanka (historical) | Statement: [Ratmalana, airportFormerRole, main international airport of Sri Lanka (historical)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: airportFormerRole
Context triple: [Ratmalana, airportFormerRole, main international airport of Sri Lanka (historical)]
  • A. formerAirportType
    Indicates that an entity previously had a specific airport classification or type, but no longer holds that status.
  • B. hasFormerAirport
    Indicates that an entity previously had an airport that is no longer in operation or no longer exists.
  • C. replacedAsMainAirportFor
    Indicates that one airport has taken over the role of being the primary or main airport serving a particular area from another airport.
  • D. formerAirportStatus chosen
    Indicates that an entity previously held the status of an airport but no longer functions as one.
  • E. airportRole
    Indicates that an entity serves a specific functional role or capacity within the context of an airport.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf2a26c81908aaf614d7c75e219 completed April 28, 2026, 9:51 p.m.
PD Predicate disambiguation batch_69e71b5177d881908f90abde14ada7dc completed April 21, 2026, 6:38 a.m.
Created at: April 16, 2026, 8:37 p.m.