Triple
T19726001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Severobaikalsk |
E473727
|
entity |
| Predicate | railConnection |
P848
|
FINISHED |
| Object | Ust-Kut |
—
|
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-Kut | Statement: [Severobaikalsk, railConnection, Ust-Kut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ust-Kut Context triple: [Severobaikalsk, railConnection, Ust-Kut]
-
A.
Ust-Kut
chosen
Ust-Kut is a town in Irkutsk Oblast, Russia, located on the Lena River and known as a regional transport hub with river port and railway connections.
-
B.
Ust-Ilimsk
Ust-Ilimsk is a Siberian city in Russia known for its large hydroelectric power station on the Angara River and its role in the region’s timber and energy industries.
-
C.
Angarsk
Angarsk is a major industrial city in southeastern Siberia, Russia, known for its petrochemical and nuclear-related facilities.
-
D.
Apatity
Apatity is an industrial and scientific town in Russia’s Murmansk Oblast, known for its phosphate mining and research institutes within the Arctic Kola Peninsula region.
-
E.
Kudymkar
Kudymkar is a town in Perm Krai, Russia, known as the main urban center of the Komi-Permyak people and a local cultural and administrative hub.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649f7bedc81908f784832c0fc10a1 |
completed | April 20, 2026, 3:44 p.m. |
Created at: April 10, 2026, 1:46 p.m.