Triple
T8947895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berezina |
E213267
|
entity |
| Predicate | mouthOfWaterBody |
P3817
|
FINISHED |
| Object | Dnieper River |
E41855
|
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: Dnieper River | Statement: [Berezina, mouthOfWaterBody, Dnieper River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dnieper River Context triple: [Berezina, mouthOfWaterBody, Dnieper River]
-
A.
Dnieper
chosen
The Dnieper is a major Eastern European river that flows through Russia, Belarus, and Ukraine before emptying into the Black Sea.
-
B.
Taras River
The Taras River is an ancient waterway in southern Italy historically associated with the Greek colony of Tarentum (modern Taranto) on the Ionian Sea.
-
C.
Vorskla River
The Vorskla River is a significant tributary of the Dnieper River in central Ukraine, known for its historical battle sites and role in regional ecology and transport.
-
D.
Kharkiv River
The Kharkiv River is a waterway in northeastern Ukraine that flows through and lends its name to the city of Kharkiv before joining the Lopan River.
-
E.
Dniester
The Dniester is a major river in Eastern Europe that flows through Ukraine and Moldova before emptying into the Black Sea.
- 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_69ca839843408190a39069a029a89f15 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66deb8ec819087a9c5eddd24c08a |
completed | April 1, 2026, 12:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d58be8a4819088c419888a879e3e |
completed | April 5, 2026, 3:22 a.m. |
Created at: March 30, 2026, 6:59 p.m.