Triple
T10970729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amazigh New Year |
E259225
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Yennayer |
E638103
|
NE 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: Yennayer | Statement: [Amazigh New Year, hasName, Yennayer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yennayer Context triple: [Amazigh New Year, hasName, Yennayer]
-
A.
Yennayer
chosen
Yennayer is the Amazigh (Berber) New Year, a traditional North African celebration marked by cultural rituals, feasts, and community gatherings.
-
B.
Têt
The Têt is a river in southern France that flows through the Pyrénées-Orientales department in the Occitanie region before reaching the Mediterranean Sea.
-
C.
Nayrouz
Nayrouz is the Coptic New Year festival, commemorating the martyrs and marking the beginning of the Coptic calendar year.
-
D.
Reyvroz
Reyvroz is a small commune in the Haute-Savoie department of southeastern France, situated in the French Alps.
-
E.
Kislev
Kislev is a late autumn/early winter month in the Hebrew calendar traditionally associated with the festival of Hanukkah.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7719a27488190b0b723cd0aba40bd |
completed | April 9, 2026, 9:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d790df108190b4a3a6fece372778 |
completed | April 18, 2026, 1 a.m. |
Created at: April 8, 2026, 9:24 p.m.