Triple
T19591857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shabbat Shekalim |
E470254
|
entity |
| Predicate | timingRule |
P46295
|
FINISHED |
| Object | Shabbat before Rosh Chodesh 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: Shabbat before Rosh Chodesh Adar | Statement: [Shabbat Shekalim, timingRule, Shabbat before Rosh Chodesh Adar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timingRule Context triple: [Shabbat Shekalim, timingRule, Shabbat before Rosh Chodesh Adar]
-
A.
usesTimingRules
Indicates that one entity applies or operates according to specified timing rules or constraints in relation to another entity or process.
-
B.
timingParameter
Indicates a relationship where one entity specifies or controls a temporal setting, constraint, or configuration parameter that determines the timing behavior of another entity or process.
-
C.
timeoutRule
Indicates a rule that defines when and under what conditions an operation, request, or process should automatically time out.
-
D.
schedulingRule
chosen
Indicates a rule or constraint that governs when, how, or under what conditions an event or task may be scheduled.
-
E.
timeType
Indicates the specific temporal category or classification associated with a time-related entity or value (e.g., duration, point in time, interval, or recurrence type).
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6405646f0819089436d5517c03047 |
completed | April 20, 2026, 3:03 p.m. |
| PD | Predicate disambiguation | batch_69e514dbdb988190b55931a8138c73e7 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.