Triple
T20142972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wetu Telu |
E491220
|
entity |
| Predicate | hasCalendarBasis |
P17591
|
FINISHED |
| Object | combination of Islamic and local ritual calendars |
—
|
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: combination of Islamic and local ritual calendars | Statement: [Wetu Telu, hasCalendarBasis, combination of Islamic and local ritual calendars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCalendarBasis Context triple: [Wetu Telu, hasCalendarBasis, combination of Islamic and local ritual calendars]
-
A.
hasCalendarFunction
Indicates that an entity possesses or supports a calendar-related capability or functionality.
-
B.
calculationBasis
Indicates the rule, method, or reference standard used as the foundation for performing a calculation in the relationship.
-
C.
hasBaseDate
Indicates that an entity is associated with a specific reference or starting date used as the basis for related calculations, schedules, or validity periods.
-
D.
hasCalendarCustom
chosen
Indicates that an entity is associated with a customized or non-default calendar configuration or behavior.
-
E.
usesJulianCalendar
Indicates that the subject follows or is based on the Julian calendar system for dating events or timekeeping.
- 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6679bcf2c8190ac6e969178d8acde |
completed | April 20, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69e54cfb0d0081908e789b9b57e96668 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:33 p.m.