Triple
T37650868
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | רבי משה איסרליש |
E937167
|
entity |
| Predicate | השתייכות הלכתית |
P72195
|
FINISHED |
| Object | מנהגי אשכנז |
—
|
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: מנהגי אשכנז | Statement: [רבי משה איסרליש, השתייכות הלכתית, מנהגי אשכנז]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: השתייכות הלכתית Context triple: [רבי משה איסרליש, השתייכות הלכתית, מנהגי אשכנז]
-
A.
מסורת חז"ל
Indicates the relationship in which something is based on, derived from, or in accordance with the rabbinic tradition and teachings of the Sages (Chazal).
-
B.
inHalachicCanon
Indicates that something is included within, recognized by, or governed according to the authoritative body of Jewish halachic (legal) texts.
-
C.
halakhicSource
Indicates a relationship where one item serves as the halakhic (Jewish legal) basis, authority, or source text for another.
-
D.
halachicSection
chosen
Indicates a relationship where a subject is classified under, or associated with, a specific section or subdivision within halachic (Jewish legal) texts or rulings.
-
E.
halakhicFunction
Indicates a relationship where something serves a role, purpose, or effect within the framework of Jewish law (halakha).
- 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb084760c8190a1554985d3c3cb7a |
completed | May 6, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69fbadf3cb548190ba3b7514f76b790a |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:18 p.m.