Triple
T113188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shabbat |
E2288
|
entity |
| Predicate | beginsWith |
P1037
|
FINISHED |
| Object | lighting Shabbat candles |
—
|
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: lighting Shabbat candles | Statement: [Shabbat, beginsWith, lighting Shabbat candles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: beginsWith Context triple: [Shabbat, beginsWith, lighting Shabbat candles]
-
A.
preambleBeginsWith
chosen
Indicates that the preamble of a document or text starts with a specified substring, phrase, or content.
-
B.
recognizedFirstBy
Indicates that one entity was the earliest or initial recognizer, identifier, or acknowledger of another entity.
-
C.
endedWith
Indicates that one event, process, or state concluded with or was finalized by another specified event, condition, or outcome.
-
D.
firstLetter
Indicates that one entity is the initial character or starting letter of another entity (typically a string or word).
-
E.
languageBegins
Indicates that a particular language starts to be used, recognized, or becomes relevant at a specific point in time or context.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a258808ff08190a06b6206f635612b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a256425a488190959d71e39e699d90 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.