Triple

T19268225
Position Surface form Disambiguated ID Type / Status
Subject Kirensk E481845 entity
Predicate servedBy P82 FINISHED
Object Kirensk Airport E1369284 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: Kirensk Airport | Statement: [Kirensk, servedBy, Kirensk Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kirensk Airport
Context triple: [Kirensk, servedBy, Kirensk Airport]
  • A. Kirensk Airport chosen
    Kirensk Airport is a regional public airport serving the town of Kirensk in Irkutsk Oblast, Russia, providing air transport connections for the surrounding area.
  • B. Staroselye Airport
    Staroselye Airport is a regional airport serving the city of Rybinsk in Yaroslavl Oblast, Russia.
  • C. Sokol Airport
    Sokol Airport is the main airport serving the city of Magadan in Russia’s Far East, handling both domestic and limited international flights.
  • D. Khrabrovo Airport
    Khrabrovo Airport is the main civilian airport serving the Russian exclave of Kaliningrad and its surrounding region.
  • E. Grabtsevo Airport
    Grabtsevo Airport is the main commercial airport serving the city of Kaluga in western Russia, providing regional and limited international air connections.
  • 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb8e1f888190a95f60fa29ca3b98 completed April 20, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a071bce5ef08190bca61ea94b5956d5 completed May 15, 2026, 1:12 p.m.
Created at: April 10, 2026, 1:29 p.m.