Triple
T3236034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yantra |
E67856
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object | Belitsa River |
E350712
|
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: Belitsa River | Statement: [Yantra, hasTributary, Belitsa River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Belitsa River Context triple: [Yantra, hasTributary, Belitsa River]
-
A.
Tundzha River
The Tundzha River is a significant river in southeastern Europe that flows through Bulgaria and Turkey before joining the Maritsa River.
-
B.
Dryanovska River
chosen
The Dryanovska River is a smaller watercourse in central Bulgaria that serves as a tributary of the Yantra River, contributing to its flow through the region.
-
C.
Angren River
The Angren River is a waterway in eastern Uzbekistan that flows through the Tashkent Region before joining the Syr Darya.
-
D.
Selemdzha River
The Selemdzha River is a significant river in Russia’s Amur Oblast, known for its remote taiga landscapes and role in the regional hydrological system.
-
E.
Blagoevgradska Bistritsa
Blagoevgradska Bistritsa is a river in southwestern Bulgaria that flows through the city of Blagoevgrad before joining the Struma 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_69ad858d27348190abb61c280b4c86a9 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaee05d34819095dbce4db6ac8613 |
completed | March 8, 2026, 5:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b33411537081908624477fca92296d |
completed | March 12, 2026, 9:45 p.m. |
Created at: March 8, 2026, 3:08 p.m.