Triple
T19591838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shabbat Shekalim |
E470254
|
entity |
| Predicate | hasHaftarah |
P47663
|
FINISHED |
| Object | II Kings 12:1–17 |
—
|
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: II Kings 12:1–17 | Statement: [Shabbat Shekalim, hasHaftarah, II Kings 12:1–17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHaftarah Context triple: [Shabbat Shekalim, hasHaftarah, II Kings 12:1–17]
-
A.
Haftarah
chosen
Indicates the relationship in which a specific prophetic reading from the Nevi'im is designated to accompany a particular Torah portion or liturgical occasion.
-
B.
hasPublicTorahReading
Indicates that a religious event or occasion includes a formal, communal reading of the Torah in public.
-
C.
hasGemara
Indicates that an entity possesses, includes, or is associated with a Gemara (a Talmudic text or study component).
-
D.
hasMasorah
Indicates that a text or manuscript is associated with, contains, or is annotated by the Masorah (the traditional Jewish textual notes and transmission apparatus).
-
E.
includesMegillot
Indicates that one entity contains or encompasses the set of texts or items referred to as Megillot.
- 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.