Triple
T21240705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Severodonetsk |
E523460
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Sievierodonetsk |
—
|
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: Sievierodonetsk | Statement: [Severodonetsk, alternativeName, Sievierodonetsk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sievierodonetsk Context triple: [Severodonetsk, alternativeName, Sievierodonetsk]
-
A.
Sievierodonetsk
chosen
Sievierodonetsk is an industrial city in eastern Ukraine that became a focal point of intense fighting during the war in the Donbas and the 2022 Russian invasion.
-
B.
Kakhovskaya
Kakhovskaya is a Moscow Metro station that serves as part of the city’s Big Circle Line.
-
C.
Chornomorske
Chornomorske is a coastal settlement in western Crimea known for its location on the Black Sea and its role as a local resort and fishing community.
-
D.
Kryvyi Rih
Kryvyi Rih is a major industrial city in central Ukraine known for its extensive iron ore mining and steel production.
-
E.
Shepetivka
Shepetivka is a city in western Ukraine known as the birthplace of prominent Russian politician Valentina Matviyenko.
- 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_69e0b513b89c81908b27147e91368db2 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735239f48819091ffe518b1aed2e8 |
completed | April 21, 2026, 8:28 a.m. |
Created at: April 16, 2026, 3:47 p.m.