Triple
T3191731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Dvina River |
E66837
|
entity |
| Predicate | hasTownOnBanks |
P26693
|
FINISHED |
| Object | Kotlas |
E303759
|
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: Kotlas | Statement: [Northern Dvina River, hasTownOnBanks, Kotlas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kotlas Context triple: [Northern Dvina River, hasTownOnBanks, Kotlas]
-
A.
Kotlas
chosen
Kotlas is a significant industrial and transport hub in northern Russia, located at the confluence of the Vychegda and Northern Dvina rivers.
-
B.
Kholmsk
Kholmsk is a port town on the western coast of Sakhalin Island in Russia, serving as an important maritime transport hub in the Sea of Japan.
-
C.
Kotzebue
Kotzebue is a remote city in northwestern Alaska located above the Arctic Circle, known as a regional hub for transportation, commerce, and Inupiat culture.
-
D.
Kurilsk
Kurilsk is a small Russian town on Iturup Island in the Kuril archipelago, serving as an administrative and fishing center in the North Pacific.
-
E.
Setka
Setka was an ancient Egyptian prince of the 4th Dynasty, likely a son of Pharaoh Djedefre, known from statues and inscriptions found at Abu Rawash.
- 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada6e8e4b48190bc7c6443fc6da900 |
completed | March 8, 2026, 4:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b24ba19b2881908a298e6fb99a058e |
completed | March 12, 2026, 5:14 a.m. |
Created at: March 8, 2026, 3:07 p.m.