Triple
T9955640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Андреевский скит |
E195439
|
entity |
| Predicate | язык литургии |
P45911
|
FINISHED |
| Object | церковнославянский язык |
—
|
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: церковнославянский язык | Statement: [Андреевский скит, язык литургии, церковнославянский язык]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: язык литургии Context triple: [Андреевский скит, язык литургии, церковнославянский язык]
-
A.
liturgicalLanguageVersion
Indicates that one entity is a specific version or form of another entity expressed in a particular liturgical language.
-
B.
usesAlsoLiturgy
Indicates that an entity additionally employs or follows a particular liturgy alongside its primary or other liturgical practices.
-
C.
liturgicalLanguageUsage
chosen
Indicates the relationship in which a particular language is used as the medium for conducting religious or liturgical rites, prayers, or ceremonies.
-
D.
liturgicalText
Indicates that one entity is a liturgical or ritual text used in the religious or ceremonial practices associated with another entity.
-
E.
liturgicalUsage
Indicates how something is used, practiced, or functions within a specific liturgical or worship context.
- 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_69ca82eaaa008190a54fa1a9f954b9ad |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb69631d08190ab2b1d1c22d46da7 |
completed | April 2, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69cd1d97c44081908730071269f07712 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:46 p.m.