Triple
T21916599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maharashtra Day |
E541195
|
entity |
| Predicate | sectorHolidayFor |
P125669
|
FINISHED |
| Object | state government offices in Maharashtra |
—
|
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: state government offices in Maharashtra | Statement: [Maharashtra Day, sectorHolidayFor, state government offices in Maharashtra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sectorHolidayFor Context triple: [Maharashtra Day, sectorHolidayFor, state government offices in Maharashtra]
-
A.
publicHolidaySector
chosen
Indicates that a public holiday applies specifically to, or is defined for, a particular sector or industry.
-
B.
hasRegionalHoliday
Indicates that a particular region observes or is associated with a specific holiday.
-
C.
holidayType
Indicates the specific category or kind of holiday associated with an event or date (e.g., public, religious, national, or personal).
-
D.
holidaySchedule
Indicates the planned dates, times, and durations during which holidays occur or are observed.
-
E.
hasHolidayAssociation
Indicates a relationship where something is connected or related to a holiday, such as by theme, usage, or occurrence.
- 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_69e0c47c4b9c8190a5586a75f5f36453 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1233858308190a877d8015db4d380 |
completed | April 28, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69e6be9ebf4c8190892df1a8e1313f88 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:43 p.m.