Triple

T15678305
Position Surface form Disambiguated ID Type / Status
Subject Tourujoki E377502 entity
Predicate region P40 FINISHED
Object Keski-Suomi E289654 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: Keski-Suomi | Statement: [Tourujoki, region, Keski-Suomi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keski-Suomi
Context triple: [Tourujoki, region, Keski-Suomi]
  • A. Keski-Pohjanmaa
    Keski-Pohjanmaa is a region in western Finland known for its coastal landscapes, rural communities, and strong Ostrobothnian cultural traditions.
  • B. Central Finland chosen
    Central Finland is a region in the heart of Finland known for its lakes, forests, and the city of Jyväskylä as its main urban and educational center.
  • C. Satakunta
    Satakunta is a historical province and region on the western coast of Finland, known for its industrial heritage, coastal landscapes, and the city of Pori.
  • D. Central Ostrobothnia
    Central Ostrobothnia is a region in western Finland known for its coastal landscapes, rural communities, and strong cultural traditions.
  • E. Pohjois-Savo
    Pohjois-Savo is a region in Eastern Finland known for its lakes, forests, and the regional center city of Kuopio.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2f1640819086efd5a73bb9734a completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff28d38a4819085bf051b566c17e7 completed May 10, 2026, 2:50 a.m.
Created at: April 10, 2026, 4:16 a.m.