Triple

T11749996
Position Surface form Disambiguated ID Type / Status
Subject EFIK E279379 entity
Predicate name P16 FINISHED
Object Tikkakoski Air Base E58140 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: Tikkakoski Air Base | Statement: [EFIK, name, Tikkakoski Air Base]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tikkakoski Air Base
Context triple: [EFIK, name, Tikkakoski Air Base]
  • A. Tikkakoski Air Base chosen
    Tikkakoski Air Base is a Finnish military airfield that serves as one of the operational bases of the Finnish Air Force.
  • B. Pirkkala Air Base
    Pirkkala Air Base is a major military airfield in Finland that serves as one of the key operational bases of the Finnish Air Force.
  • C. Kauhava Air Base
    Kauhava Air Base is a former major Finnish Air Force airfield in western Finland that long served as the country’s primary pilot training base.
  • D. Rovaniemi Air Base
    Rovaniemi Air Base is a major Finnish military airfield in northern Finland that serves as a key operational base for the Finnish Air Force, particularly for Arctic and northern airspace operations.
  • E. Lappeenranta Airport
    Lappeenranta Airport is a regional airport in southeastern Finland that serves the city of Lappeenranta and provides both domestic and international flight 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_69d6ab01038c819080714901502c84fc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a508b0c4819082fbcc27d559ea2f completed April 10, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69f01a0492b48190b6f2e3cf36b4f537 completed April 28, 2026, 2:23 a.m.
Created at: April 8, 2026, 9:41 p.m.