Triple
T6763145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banja Luka |
E154645
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Vrbas River |
E370919
|
NE FINISHED |
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: Vrbas River | Statement: [Banja Luka, locatedOnRiver, Vrbas River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vrbas River Context triple: [Banja Luka, locatedOnRiver, Vrbas River]
-
A.
Vrbas
chosen
Vrbas is a river in western Bosnia and Herzegovina that flows through cities like Banja Luka before joining the Sava River.
-
B.
Vrbas
Vrbas is a town and municipality in the Bačka region of northern Serbia, known as a local administrative, industrial, and transportation center.
-
C.
Savica River
The Savica River is a short but notable river in northwestern Slovenia, famous for its picturesque waterfall source in the Julian Alps and its role in feeding Lake Bohinj.
-
D.
Bojana River
The Bojana River is a major waterway in the Balkans that flows from Lake Skadar to the Adriatic Sea, forming part of the border between Montenegro and Albania.
-
E.
Vanj River
The Vanj River is a mountain river in Tajikistan that flows through the Vanj Valley in the Pamir region before joining the Panj River.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c688109c1c8190added9a221292af0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2160a2c8190837c608a3509c62c |
completed | March 27, 2026, 6:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c748a839648190a2d6875a8465579b |
completed | March 28, 2026, 3:19 a.m. |
Created at: March 27, 2026, 2:12 p.m.