Triple
T15484939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prairial |
E377020
|
entity |
| Predicate | follows |
P134
|
FINISHED |
| Object | Floréal |
E375146
|
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: Floréal | Statement: [Prairial, follows, Floréal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Floréal Context triple: [Prairial, follows, Floréal]
-
A.
Floréal
chosen
Floréal is the eighth springtime month of the French Republican Calendar, named to evoke the flowering period of the year.
-
B.
Fructidor
Fructidor is the twelfth and final month of the French Republican Calendar, corresponding roughly to late August and early September and associated with the fruit harvest.
-
C.
Pluviôse
Pluviôse is the fifth month of the French Republican Calendar, corresponding roughly to late January and early February and named for its typically rainy weather.
-
D.
Prairial
Prairial is the ninth month of the French Republican Calendar, corresponding roughly to late May and most of June and associated with the flowering of meadows.
-
E.
Vendémiaire
Vendémiaire is the first month of the French Republican Calendar, corresponding roughly to late September and early October and associated with the grape harvest.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f8e6ff08190b130b3a38f4190e7 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff56b9238081908fb2e6a7dcc2296f |
completed | May 9, 2026, 3:46 p.m. |
Created at: April 10, 2026, 3:46 a.m.