Triple
T22652722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Марий Эл Республикасе |
E559135
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Kozmodemyansk |
—
|
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: Kozmodemyansk | Statement: [Марий Эл Республикасе, contains, Kozmodemyansk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kozmodemyansk Context triple: [Марий Эл Республикасе, contains, Kozmodemyansk]
-
A.
Kozmodemyansk
chosen
Kozmodemyansk is a historic town in the Mari El Republic of Russia, situated on the Volga River and known for its traditional Mari culture and wooden architecture.
-
B.
Kosmodemyanskaya
Kosmodemyanskaya is a Russian surname most famously borne by Zoya Kosmodemyanskaya, a celebrated Soviet partisan and Hero of the Soviet Union during World War II.
-
C.
Kozhedub
Kozhedub is a Slavic surname most famously borne by Ivan Kozhedub, a highly decorated Soviet World War II fighter ace.
-
D.
Yelets
Yelets is a historic city in western Russia known for its medieval origins, traditional lace-making, and role as a regional cultural and economic center.
-
E.
Vyartsilya
Vyartsilya is a small urban-type settlement in the Republic of Karelia, Russia, near the border with Finland.
- 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_69e245489dd88190b1f674acf61c8769 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1703d7d648190aafe275cd04c47cf |
completed | April 29, 2026, 2:43 a.m. |
Created at: April 17, 2026, 3:06 p.m.