Triple
T8269327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kosach family |
E193382
|
entity |
| Predicate | languageOfCulturalActivity |
P11341
|
FINISHED |
| Object | Ukrainian |
—
|
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: Ukrainian | Statement: [Kosach family, languageOfCulturalActivity, Ukrainian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfCulturalActivity Context triple: [Kosach family, languageOfCulturalActivity, Ukrainian]
-
A.
languageOfEvent
Indicates the language in which an event is conducted, presented, or communicated.
-
B.
languageOfVenue
Indicates the language primarily used or officially designated for communication at a given venue.
-
C.
hasCulturalExpression
Indicates that an entity embodies, manifests, or is associated with a particular cultural form, practice, or expression.
-
D.
isCulturalLanguageOf
chosen
Indicates that a language serves as a primary medium of cultural expression, identity, and heritage for a particular group, community, or region.
-
E.
culturalType
Indicates the classification of something according to its cultural category, style, or tradition.
- 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_69ca82e14ae481908ffdb822cd2192bc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb795127ac81908196008f5579f83f |
completed | March 31, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69cb70a4525481909399d313a6247ace |
completed | March 31, 2026, 6:58 a.m. |
Created at: March 30, 2026, 5:50 p.m.