Triple
T820117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyiv |
E17733
|
entity |
| Predicate | locatedOnRiver |
P165
|
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: [Kyiv, locatedOnRiver, Dnieper River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dnieper River Context triple: [Kyiv, locatedOnRiver, 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.
Dniester
The Dniester is a major river in Eastern Europe that flows through Ukraine and Moldova before emptying into the Black Sea.
-
C.
Kuban River
The Kuban River is a major river in the North Caucasus region of Russia that flows through the Krasnodar Krai before emptying into the Sea of Azov.
-
D.
Daugava River
The Daugava River is a major Eastern European river flowing through Russia, Belarus, and Latvia before emptying into the Baltic Sea.
-
E.
Vistula River
The Vistula River is Poland’s longest and most important river, flowing from the Carpathian Mountains to the Baltic Sea and passing through major cities such as Kraków and Warsaw.
- 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_69a4937bcaac8190a322524ac6f45a5a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab6698d881908d8c5d91259f97ec |
completed | March 1, 2026, 9:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac4bfac5cc8190a5fba1c5da98391d |
completed | March 7, 2026, 4:02 p.m. |
Created at: March 1, 2026, 7:38 p.m.