Triple
T5150883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Choral Evensong |
E116189
|
entity |
| Predicate | hasLiturgicalType |
P13039
|
FINISHED |
| Object | Evening prayer |
—
|
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: Evening prayer | Statement: [Choral Evensong, hasLiturgicalType, Evening prayer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLiturgicalType Context triple: [Choral Evensong, hasLiturgicalType, Evening prayer]
-
A.
hasLiturgicalContext
Indicates that something is associated with, used in, or relevant to a formal religious or liturgical setting or practice.
-
B.
hasLiturgicalMention
Indicates that one entity is referenced or mentioned within the liturgical texts, practices, or rites associated with another entity.
-
C.
hasPrimaryLiturgicalForm
chosen
Indicates that an entity is associated with its main or officially recognized liturgical form used in worship or religious practice.
-
D.
hasLiturgicalExpression
Indicates that one entity expresses, embodies, or is manifested through the liturgical practices, rites, or worship forms of another entity.
-
E.
hasLiturgicalStructure
Indicates that something possesses an established form or order of worship, ritual, or liturgical arrangement.
- 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_69bd445d94788190b72e2cc563120995 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd79c1354c81908176703b4853c1a4 |
completed | March 20, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69bd77b0fbb88190851e2d7ae1bdcc09 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:44 p.m.