Triple
T20137632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harju maakond |
E491063
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Raasiiku Parish |
—
|
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: Raasiiku Parish | Statement: [Harju maakond, contains, Raasiiku Parish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raasiiku Parish Context triple: [Harju maakond, contains, Raasiiku Parish]
-
A.
Raasiku Parish
chosen
Raasiku Parish is a rural municipality in northern Estonia, located in Harju County and known for its small settlements and proximity to Tallinn.
-
B.
Luunja Parish
Luunja Parish is a rural municipality in eastern Estonia known for its agricultural landscape and proximity to the city of Tartu.
-
C.
Saku Parish
Saku Parish is a rural municipality in northern Estonia known for its proximity to Tallinn and its mix of small-town communities, forests, and agricultural areas.
-
D.
Kose Parish
Kose Parish is a rural municipality in northern Estonia known for its small towns, forests, and agricultural landscapes within Harju County.
-
E.
Nõo Parish
Nõo Parish is a rural municipality in southeastern Estonia known for its small communities, forests, and proximity to the city of Tartu.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6676879f48190a59da04393d2a8cc |
completed | April 20, 2026, 5:50 p.m. |
Created at: April 11, 2026, 11:32 p.m.