Triple
T15454456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nivôse |
E371732
|
entity |
| Predicate | correspondsRoughlyToGregorianPeriod |
P16936
|
FINISHED |
| Object | late December to early January |
—
|
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: late December to early January | Statement: [Nivôse, correspondsRoughlyToGregorianPeriod, late December to early January]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondsRoughlyToGregorianPeriod Context triple: [Nivôse, correspondsRoughlyToGregorianPeriod, late December to early January]
-
A.
correspondsRoughlyToGregorianMonths
chosen
Indicates that one or more time periods or units align approximately, but not exactly, with specific months in the Gregorian calendar.
-
B.
hasApproxGregorianStart
Indicates that an entity has an associated start date expressed as an approximate value in the Gregorian calendar.
-
C.
usesJulianCalendar
Indicates that the subject follows or is based on the Julian calendar system for dating events or timekeeping.
-
D.
accuracyComparedToJulian
Indicates how the accuracy of something compares to that of the Julian calendar as a reference standard.
-
E.
dateRelativeToGregorian
Indicates how a given date is positioned or expressed in relation to the standard Gregorian calendar date.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f131b1481909ff099c3b844ee07 |
completed | April 16, 2026, 1:44 a.m. |
| PD | Predicate disambiguation | batch_69ded28276f481908c2038bb301e57cf |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:31 a.m.