Triple

T22234293
Position Surface form Disambiguated ID Type / Status
Subject Kokemäenjoki E549547 entity
Predicate flowsThroughRegion P285 FINISHED
Object Satakunta 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: Satakunta | Statement: [Kokemäenjoki, flowsThroughRegion, Satakunta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Satakunta
Context triple: [Kokemäenjoki, flowsThroughRegion, Satakunta]
  • A. Satakunta chosen
    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.
  • B. Keski-Pohjanmaa
    Keski-Pohjanmaa is a region in western Finland known for its coastal landscapes, rural communities, and strong Ostrobothnian cultural traditions.
  • C. Päijät-Häme
    Päijät-Häme is a region in southern Finland known for its lakes, forests, and the city of Lahti as its main urban center.
  • D. Pohjois-Savo
    Pohjois-Savo is a region in Eastern Finland known for its lakes, forests, and the regional center city of Kuopio.
  • E. Keski-Suomi region
    The Keski-Suomi region, also known as Central Finland, is an inland region of Finland centered around the city of Jyväskylä and characterized by its numerous lakes, forests, and role as a cultural and educational hub.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf61504819093e70bee4c575d1c completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:38 p.m.