Triple
T21208256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ösel–Wiek Diocese |
E522646
|
entity |
| Predicate | historicalRegion |
P915
|
FINISHED |
| Object | Läänemaa |
—
|
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: Läänemaa | Statement: [Ösel–Wiek Diocese, historicalRegion, Läänemaa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Läänemaa Context triple: [Ösel–Wiek Diocese, historicalRegion, Läänemaa]
-
A.
Lääne maakond
chosen
Lääne maakond is a county in western Estonia known for its coastal landscapes, historic towns, and maritime heritage.
-
B.
Virumaa
Virumaa is a historical region in northern Estonia, known for its medieval heritage, coastal landscapes, and role as one of the country’s traditional cultural provinces.
-
C.
Järvamaa
Järvamaa is a historical region in central Estonia known for its rural landscapes, forests, and small towns such as Paide.
-
D.
Uusimaa
Uusimaa is a coastal region in southern Finland that includes the capital Helsinki and is known for its significant Swedish-speaking population and economic importance.
-
E.
Southeastern Estonia
Southeastern Estonia is a culturally distinct region of Estonia known for its Võro language heritage, rolling landscapes, and rich folk traditions.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734362c788190bc1b96d3b84c0ad1 |
completed | April 21, 2026, 8:24 a.m. |
Created at: April 16, 2026, 3:25 p.m.