Triple

T15678237
Position Surface form Disambiguated ID Type / Status
Subject Jyväskylä railway station E377500 entity
Predicate hasConnectionTo P845 FINISHED
Object Äänekoski 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: Äänekoski | Statement: [Jyväskylä railway station, hasConnectionTo, Äänekoski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Äänekoski
Context triple: [Jyväskylä railway station, hasConnectionTo, Äänekoski]
  • A. Äänekoski chosen
    Äänekoski is a Finnish town in Central Finland known for its forest industry, lakeside landscapes, and role as a regional industrial and logistics hub.
  • B. Kuokkala
    Kuokkala is a former Finnish locality on the Karelian Isthmus, now known as Repino in Saint Petersburg, Russia.
  • C. Kuokkala
    Kuokkala is a residential district of the city of Jyväskylä in central Finland, known for its lakeside location and distinctive bridge connection to the city center.
  • D. Kokkola
    Kokkola is a coastal city in western Finland known for its maritime heritage and role as a military and naval hub.
  • E. Heinola
    Heinola is a small Finnish town in the Päijät-Häme region, known for its lakeside scenery and traditional wooden architecture.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2f1640819086efd5a73bb9734a completed April 16, 2026, 2:53 a.m.
Created at: April 10, 2026, 4:16 a.m.