Triple
T20095002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indigirka River |
E496375
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Ust-Nera |
—
|
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: Ust-Nera | Statement: [Indigirka River, nearbySettlement, Ust-Nera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ust-Nera Context triple: [Indigirka River, nearbySettlement, Ust-Nera]
-
A.
Ust-Nera
chosen
Ust-Nera is a remote urban-type settlement in northeastern Russia’s Sakha Republic, known for its extremely cold climate and role as a regional mining and transport hub in the upper Indigirka River basin.
-
B.
Verkhorechye
Verkhorechye is a small settlement located near the Alma River, likely in the Crimean region of Eastern Europe.
-
C.
Verkhny Ufaley
Verkhny Ufaley is an industrial town in Russia known for its metallurgical and mining industries.
-
D.
Urzhum
Urzhum is a small historic town in Kirov Oblast, Russia, known as the birthplace of prominent Soviet leader Sergei Kirov.
-
E.
Nagatinskaya
Nagatinskaya is a Moscow Metro station serving the Serpukhovsko–Timiryazevskaya Line in the Nagatinsky Zaton area of southern Moscow.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6666b891c8190b4e4a60b73728771 |
completed | April 20, 2026, 5:46 p.m. |
Created at: April 11, 2026, 11:24 p.m.