Triple
T6369008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midnight Office |
E143298
|
entity |
| Predicate | liturgicalDayPosition |
P70234
|
FINISHED |
| Object | between Compline and Matins |
—
|
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: between Compline and Matins | Statement: [Midnight Office, liturgicalDayPosition, between Compline and Matins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: liturgicalDayPosition Context triple: [Midnight Office, liturgicalDayPosition, between Compline and Matins]
-
A.
positionInHolyWeek
Indicates the specific place or order that a day, event, or observance occupies within the sequence of days in Holy Week.
-
B.
positionInRomanCalendar
Indicates the ordinal placement or rank that something occupies within the sequence of months or days in the Roman calendar.
-
C.
hasLiturgicalDay
Indicates that a particular date, event, or context is associated with a specific liturgical day within a religious calendar.
-
D.
dayRelativeToEaster
Indicates the temporal offset of a given day relative to the date of Easter in a specific year (e.g., days before or after Easter Sunday).
-
E.
liturgicalSeasonContext
Indicates the specific liturgical season within which a religious action, event, or text takes place or is understood.
- F. None of above. chosen
Provenance (4 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_69c008d8c61081908bcaf61510d881ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c068265a7481908571be7ea4ac11b7 |
completed | March 22, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69c060ee055081908c79a1d151bd74cd |
completed | March 22, 2026, 9:36 p.m. |
| PDg | Predicate description generation | batch_69c0623bb29081908bfdfb84a07ece90 |
completed | March 22, 2026, 9:42 p.m. |
Created at: March 22, 2026, 4:33 p.m.