Triple
T27406007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amanda Woods |
E691999
|
entity |
| Predicate | spendsHolidayDuring |
P80111
|
FINISHED |
| Object | Christmas |
—
|
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: Christmas | Statement: [Amanda Woods, spendsHolidayDuring, Christmas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spendsHolidayDuring Context triple: [Amanda Woods, spendsHolidayDuring, Christmas]
-
A.
setDuringHoliday
chosen
Indicates that an event, action, or state occurs within the time period of a specified holiday.
-
B.
holidayType
Indicates the specific category or kind of holiday associated with an event or date (e.g., public, religious, national, or personal).
-
C.
hasUseDuringVacation
Indicates that something is intended to be used or is applicable specifically during a vacation period.
-
D.
hasHolidayAssociation
Indicates a relationship where something is connected or related to a holiday, such as by theme, usage, or occurrence.
-
E.
typicalHolidaySeasonOutput
Indicates the usual or expected level of output or activity that occurs during the holiday season.
- 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_69ef5205fc808190ad3efc5525b8e6d6 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62cd639388190bc2e0daf2aa164e3 |
completed | May 2, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:30 p.m.