Triple
T20261120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sukhona River |
E498836
|
entity |
| Predicate | hasCityOnBank |
P7935
|
FINISHED |
| Object | Sokol |
—
|
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: Sokol | Statement: [Sukhona River, hasCityOnBank, Sokol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sokol Context triple: [Sukhona River, hasCityOnBank, Sokol]
-
A.
Sokol
Sokol is a Moscow Metro station on the Zamoskvoretskaya Line, serving the Sokol District in the north of the city.
-
B.
Sokol
Sokol is a small settlement in Russia’s Magadan Oblast that serves as the community adjacent to and associated with Magadan Airport.
-
C.
Sokol
chosen
Sokol is a town in Russia known as an industrial and administrative center within Vologda Oblast.
-
D.
Sokol
Sokol is a Czech-based gymnastics and physical education movement and organization that became a key force in promoting national identity, civic values, and mass fitness across Central Europe.
-
E.
Sokol Kiev
Sokol Kiev was an ice hockey club from Kyiv that competed at the top level of Soviet hockey in the Soviet Championship League.
- 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e674ca77c081909cd2f44ccfe3662d |
completed | April 20, 2026, 6:47 p.m. |
Created at: April 11, 2026, 11:41 p.m.