Triple
T22422896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sext |
E554293
|
entity |
| Predicate | positionInDay |
P138971
|
FINISHED |
| Object | midday |
—
|
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: midday | Statement: [Sext, positionInDay, midday]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInDay Context triple: [Sext, positionInDay, midday]
-
A.
positionInMonth
Indicates the specific ordinal position or occurrence of something within a given month (e.g., first, second, third).
-
B.
liturgicalDayPosition
Indicates the specific placement or order of a liturgical day within a liturgical calendar, season, or sequence of observances.
-
C.
positionInGregorianCalendar
Indicates the specific placement or ordering of a time-related entity within the structure of the Gregorian calendar.
-
D.
positionInCivilYear
Indicates the specific point or ordering of something within the sequence of time units that make up a civil (calendar) year.
-
E.
segmentOfDaypart
chosen
Indicates that one time segment occurs within or corresponds to a specific part of the day (e.g., morning, afternoon, evening).
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15a2a1a3c8190a649ee4df2429e69 |
completed | April 29, 2026, 1:08 a.m. |
| PD | Predicate disambiguation | batch_69e8989495bc81909d2699fce5992e28 |
completed | April 22, 2026, 9:44 a.m. |
Created at: April 16, 2026, 8:47 p.m.