Triple
T9669924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kassia |
E233998
|
entity |
| Predicate | hasRoleInLiturgy |
P11534
|
FINISHED |
| Object | composer of hymns for Holy Week |
—
|
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: composer of hymns for Holy Week | Statement: [Kassia, hasRoleInLiturgy, composer of hymns for Holy Week]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoleInLiturgy Context triple: [Kassia, hasRoleInLiturgy, composer of hymns for Holy Week]
-
A.
liturgicalRole
chosen
Indicates the specific function or position an entity holds within a religious or liturgical context.
-
B.
hasLiturgicalRank
Indicates that an entity is assigned a specific status or level within a liturgical or religious ceremonial hierarchy.
-
C.
hasLiturgicalCategory
Indicates that something is classified under a particular liturgical category within a religious or worship-related system.
-
D.
hasLiturgicalNature
Indicates that something possesses a liturgical character or function, typically relating to formal religious worship or rites.
-
E.
isPartOfLiturgicalUnit
Indicates that one element belongs to, and functions as a component within, a larger liturgical unit or structure.
- 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_69ca848f55e48190b3f67252571c3d45 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c3ec17081908c2da74a1d1f49da |
completed | April 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b3239c8190b3ae3b9bd121e4bd |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:15 p.m.