Triple
T12788355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Protivín |
E305690
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Blanice River |
—
|
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: Blanice River | Statement: [Protivín, locatedOnRiver, Blanice River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blanice River Context triple: [Protivín, locatedOnRiver, Blanice River]
-
A.
Blanice River
chosen
The Blanice River is a river in the Czech Republic that flows through the town of Vlašim and forms part of the Sázava River basin.
-
B.
Prądnik River
The Prądnik River is a small river in southern Poland known for carving the picturesque limestone valley that runs through Ojców and the surrounding Ojców National Park.
-
C.
Wieprz River
The Wieprz River is a major river in eastern Poland that flows through the Lublin region before joining the Vistula River.
-
D.
Glazne River
The Glazne River is a mountain river in southwestern Bulgaria that flows through the town of Bansko in the Pirin region.
-
E.
Radbuza River
The Radbuza River is a river in the Czech Republic that flows through the Plzeň Region and contributes to the formation of the Berounka River.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e6a61f48190972e241e70bc392c |
completed | April 10, 2026, 9:40 p.m. |
Created at: April 9, 2026, 5:30 p.m.