Triple
T17278247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lodeynoye Pole |
E419447
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Svir River |
—
|
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: Svir River | Statement: [Lodeynoye Pole, locatedOnRiver, Svir River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Svir River Context triple: [Lodeynoye Pole, locatedOnRiver, Svir River]
-
A.
Svir River
chosen
The Svir River is a waterway in northwestern Russia that links Lake Onega to Lake Ladoga and forms part of the Volga–Baltic waterway system.
-
B.
Votka River
The Votka River is a smaller watercourse in Russia that feeds into the larger Kama River within the Volga basin.
-
C.
Vologda River
The Vologda River is a waterway in northwestern Russia that flows through the city of Vologda and forms part of the region’s historical and economic transport network.
-
D.
Vozha River
The Vozha River is a waterway in western Russia historically notable as the site of a major 14th-century battle between the Grand Duchy of Moscow and the Golden Horde.
-
E.
Yèvre River
The Yèvre River is a waterway in central France that flows through the city of Bourges and forms part of the region’s local river network.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e43327b048819095fbd93b2105533a |
completed | April 19, 2026, 1:43 a.m. |
Created at: April 10, 2026, 5:40 a.m.