Triple
T31248597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | יששכר |
E796753
|
entity |
| Predicate | שבט יששכר – שותפות |
P171635
|
FINISHED |
| Object | שותפות יששכר וזבולון בפרנסה ותורה |
—
|
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: שותפות יששכר וזבולון בפרנסה ותורה | Statement: [יששכר, שבט יששכר – שותפות, שותפות יששכר וזבולון בפרנסה ותורה]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: שבט יששכר – שותפות Context triple: [יששכר, שבט יששכר – שותפות, שותפות יששכר וזבולון בפרנסה ותורה]
-
A.
שבט יששכר – תפקיד מסורתי
chosen
Indicates a traditional role or function that is historically or customarily associated with the Tribe of Issachar.
-
B.
שבט
Indicates a relationship of belonging or association between an entity and a tribe or clan.
-
C.
ברכת יעקב
Indicates the act of Jacob bestowing a blessing upon another entity.
-
D.
סב
Indicates a familial relationship where one entity is the grandfather of another.
-
E.
שירת ב
Indicates that one entity served in or was on active duty within an organization, institution, or unit associated with the other entity.
- 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 9:11 p.m.