Triple
T17938887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nepali Bikram Samvat |
E448536
|
entity |
| Predicate | approximateOffsetFromGregorian |
P84678
|
FINISHED |
| Object | 56–57 years ahead |
—
|
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: 56–57 years ahead | Statement: [Nepali Bikram Samvat, approximateOffsetFromGregorian, 56–57 years ahead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateOffsetFromGregorian Context triple: [Nepali Bikram Samvat, approximateOffsetFromGregorian, 56–57 years ahead]
-
A.
dateRelativeToGregorian
Indicates how a given date is positioned or expressed in relation to the standard Gregorian calendar date.
-
B.
calendarYearOffsetFromGregorian
chosen
Indicates the number of whole calendar years by which a given calendar system is offset relative to the Gregorian calendar.
-
C.
accuracyComparedToJulian
Indicates how the accuracy of something compares to that of the Julian calendar as a reference standard.
-
D.
hasApproxGregorianStart
Indicates that an entity has an associated start date expressed as an approximate value in the Gregorian calendar.
-
E.
relationshipToGregorianCalendar
Indicates how a given calendar date or system corresponds or relates to the Gregorian calendar.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad9455fc81908bf595f9ed42c624 |
completed | April 19, 2026, 10:25 a.m. |
| PD | Predicate disambiguation | batch_69e3f8e713d481908b4a126258c18b63 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.