Triple
T25463086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amazigh calendar |
E638102
|
entity |
| Predicate | YennayerCorrespondsTo |
P92267
|
FINISHED |
| Object | Amazigh New Year |
—
|
NE NERFINISHED |
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: Amazigh New Year | Statement: [Amazigh calendar, YennayerCorrespondsTo, Amazigh New Year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: YennayerCorrespondsTo Context triple: [Amazigh calendar, YennayerCorrespondsTo, Amazigh New Year]
-
A.
newYearCoincidesWith
chosen
Indicates that the occurrence of a new year happens at the same time as another specified event or time period.
-
B.
newYearDateGregorian
Indicates the specific calendar date on which New Year’s Day occurs according to the Gregorian calendar.
-
C.
newYearOccursIn
Indicates that the celebration or observance of New Year takes place within a specified temporal or calendrical context (such as a particular month, season, or year).
-
D.
newYearObservedIn
Indicates that a particular New Year celebration or observance takes place in or is recognized within a specified location or region.
-
E.
celebratedDay
Indicates that a particular day is observed, honored, or festively recognized in association with an entity or event.
- 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_69e75db8bab08190baca80b4a8c315fd |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f72dd1788190a5a74326054e6822 |
completed | May 2, 2026, 1:07 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 2:13 p.m.