Triple

T1470385
Position Surface form Disambiguated ID Type / Status
Subject Finnair E27121 entity
Predicate hub P423 FINISHED
Object Helsinki Airport E87879 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: Helsinki Airport | Statement: [Finnair, hub, Helsinki Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helsinki Airport
Context triple: [Finnair, hub, Helsinki Airport]
  • A. Helsinki Airport chosen
    Helsinki Airport is Finland’s main international air hub, located near Helsinki and serving as a major gateway between Europe and Asia.
  • B. 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.
  • C. Kemi-Tornio Airport
    Kemi-Tornio Airport is a regional airport in Finnish Lapland serving the twin towns of Kemi and Tornio, providing domestic connections and access to the northern Arctic area.
  • D. Stockholm Arlanda Airport
    Stockholm Arlanda Airport is Sweden’s largest and busiest international airport, serving as the primary gateway to Stockholm and a major hub for Scandinavian and European air traffic.
  • E. Stockholm Bromma Airport
    Stockholm Bromma Airport is a regional airport near central Stockholm, Sweden, primarily serving domestic and short-haul European flights.
  • 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_69a496d25d6881909dbd84f86d763992 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c5d9dd4c8190ba840a9255cd1293 completed March 1, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad15a74fbc8190b53511713032dc63 completed March 8, 2026, 6:22 a.m.
Created at: March 1, 2026, 8:01 p.m.