Triple
T3072426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shushan Purim |
E64054
|
entity |
| Predicate | occursRelativeToPurim |
P2317
|
FINISHED |
| Object | day after the 14th of Adar |
—
|
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: day after the 14th of Adar | Statement: [Shushan Purim, occursRelativeToPurim, day after the 14th of Adar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occursRelativeToPurim Context triple: [Shushan Purim, occursRelativeToPurim, day after the 14th of Adar]
-
A.
timeframeRelativeToPassover
Indicates the temporal relationship of an event or action to the time of Passover (e.g., before, during, or after Passover).
-
B.
linkedToJewishHoliday
chosen
Indicates that something has a direct association or connection with a specific Jewish holiday.
-
C.
timingRelativeToYomKippur
Indicates how the timing of an event is positioned in relation to Yom Kippur (e.g., before, during, or after the holiday).
-
D.
occursOnOrAround
Indicates that an event or action takes place on a specific date or within a small, approximate time window surrounding that date.
-
E.
containsFixedFeasts
Indicates that an entity includes or encompasses specific feasts that occur on fixed, recurring calendar dates.
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada14c8bd881909cf1bb2649ba36db |
completed | March 8, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69ad9625b30c819099ef9349c91d7b25 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:02 p.m.