Triple
T17351307
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savica Waterfall |
E421817
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Ukanc |
—
|
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: Ukanc | Statement: [Savica Waterfall, nearbySettlement, Ukanc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ukanc Context triple: [Savica Waterfall, nearbySettlement, Ukanc]
-
A.
Ukanc
chosen
Ukanc is a small, scenic settlement in Slovenia’s Julian Alps, known as a tranquil gateway to Lake Bohinj and the surrounding Triglav National Park.
-
B.
Ukaan
Ukaan is a little-documented Niger-Congo language spoken by a small community in southwestern Nigeria.
-
C.
Uzkoye
Uzkoye is a historic estate and former village in the south of Moscow, Russia, known for its noble residences and integration into the modern city.
-
D.
Uzgen
Uzgen is an ancient city in present-day Kyrgyzstan, historically significant as a major political and cultural center along the Silk Road and a former capital of the Kara-Khanid Khanate.
-
E.
Alacakaya
Alacakaya is a small town and district in eastern Turkey known for its marble quarries and location within Elazığ Province.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a2ca0708190aae8306ec3a6f2a7 |
completed | April 19, 2026, 2:13 a.m. |
Created at: April 10, 2026, 5:44 a.m.