Triple
T3504862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thanksgiving Day |
E74051
|
entity |
| Predicate | legalHolidayIn |
P3157
|
FINISHED |
| Object | all U.S. states |
—
|
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: all U.S. states | Statement: [Thanksgiving Day, legalHolidayIn, all U.S. states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalHolidayIn Context triple: [Thanksgiving Day, legalHolidayIn, all U.S. states]
-
A.
holidayType
Indicates the specific category or kind of holiday associated with an event or date (e.g., public, religious, national, or personal).
-
B.
holidaySchedule
Indicates the planned dates, times, and durations during which holidays occur or are observed.
-
C.
hasOfficialHoliday
Indicates that a particular date, event, or period is formally recognized as an official holiday by an authority or governing body.
-
D.
nationalHoliday
Indicates that a particular day is officially recognized and observed as a national holiday by a country or nation.
-
E.
isFederalHoliday
chosen
Indicates that a given day is officially recognized as a federal holiday by the national government.
- 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbf22b1c8190956141d8fb924210 |
completed | March 8, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69adae0cd8b0819099da300af09880da |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.