Triple
T7394341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Станіслав Вікентійович Косіор |
E170582
|
entity |
| Predicate | officeEndTime (Перший секретар ЦК КП(б)У) |
P40396
|
FINISHED |
| Object | січень 1938 |
—
|
LITERAL 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: січень 1938 | Statement: [Станіслав Вікентійович Косіор, officeEndTime (Перший секретар ЦК КП(б)У), січень 1938]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeEndTime (Перший секретар ЦК КП(б)У) Context triple: [Станіслав Вікентійович Косіор, officeEndTime (Перший секретар ЦК КП(б)У), січень 1938]
-
A.
firstSecretaryTermEnd
Indicates the date or point in time when an entity’s first term serving as a secretary comes to an end.
-
B.
endTimeOfPositionFirstSecretary
chosen
Indicates the date and time when an entity’s tenure or role as First Secretary comes to an end.
-
C.
formerFirstSecretary
Indicates that the subject previously held, but no longer holds, the position of First Secretary in relation to the object.
-
D.
officeEndTime (Governor of Kursk Oblast)
Indicates the time at which the Governor of Kursk Oblast’s term in office concludes.
-
E.
firstSecretaryTermStart
Indicates the date on which an entity’s first term as a secretary officially begins.
- F. None of above.
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_69c68a5f04188190ac266569c9280347 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f2263b48819089319a2a2f0d3357 |
completed | March 27, 2026, 9:09 p.m. |
| PD | Predicate disambiguation | batch_69c6f0309cc88190b55d278969400294 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:09 p.m.