Triple
T15678158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jyväskylä Airport |
E377499
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Tikkakoski |
—
|
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: Tikkakoski | Statement: [Jyväskylä Airport, locatedIn, Tikkakoski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tikkakoski Context triple: [Jyväskylä Airport, locatedIn, Tikkakoski]
-
A.
Tikkakoski
chosen
Tikkakoski is a district in Jyväskylä, Finland, known for its military air base and role as a key center for the Finnish Air Force.
-
B.
Savukoski
Savukoski is a sparsely populated municipality in Finnish Lapland known for its vast wilderness areas and traditional reindeer herding culture.
-
C.
Kuusankoski
Kuusankoski is a town in southern Finland known historically for its paper industry and location along the Kymijoki River.
-
D.
Taivalkoski
Taivalkoski is a rural municipality in Northern Ostrobothnia, Finland, known for its forests, lakes, and outdoor recreation opportunities.
-
E.
Valkeakoski
Valkeakoski is a town and municipality in the Pirkanmaa region of southern Finland, known for its paper industry and lakeside setting.
- 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.