Triple

T23005718
Position Surface form Disambiguated ID Type / Status
Subject Mariehamn Airport E572761 entity
Predicate operator P179 FINISHED
Object Finavia NE NERFINISHED

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: Finavia | Statement: [Mariehamn Airport, operator, Finavia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Finavia
Context triple: [Mariehamn Airport, operator, Finavia]
  • A. Finavia chosen
    Finavia is the Finnish state-owned company responsible for operating and maintaining Finland’s network of airports and air navigation services.
  • B. Helsinki Airport
    Helsinki Airport is Finland’s main international air hub, located near Helsinki and serving as a major gateway between Europe and Asia.
  • C. Turku Airport
    Turku Airport is an international airport in southwestern Finland serving the city of Turku and the surrounding region with passenger and cargo flights.
  • D. Tampere–Pirkkala Airport
    Tampere–Pirkkala Airport is a Finnish international airport serving the Tampere region, handling both civilian air traffic and military operations.
  • E. Savonlinna Airport
    Savonlinna Airport is a small regional airport in Savonlinna, Finland, providing domestic air connections for the surrounding South Savo area.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18356417881908c8d6ee56bdc85f5 completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:51 p.m.