Triple
T36710956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tractate Shekalim |
E906792
|
entity |
| Predicate | jerusalemTalmudStatus |
P37924
|
FINISHED |
| Object | has full Yerushalmi Gemara |
—
|
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: has full Yerushalmi Gemara | Statement: [Tractate Shekalim, jerusalemTalmudStatus, has full Yerushalmi Gemara]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: jerusalemTalmudStatus Context triple: [Tractate Shekalim, jerusalemTalmudStatus, has full Yerushalmi Gemara]
-
A.
hasJerusalemTalmud
chosen
Indicates that an entity possesses, is associated with, or is characterized by the Jerusalem Talmud.
-
B.
hasJerusalemTalmudChapters
Indicates that an entity (such as a tractate or section) is associated with a specified number or set of chapters in the Jerusalem Talmud.
-
C.
statusOfJerusalem
Indicates the political or legal condition, control, or recognition of Jerusalem at a given time.
-
D.
halakhicStatus
Indicates the formal standing or classification of an entity according to Jewish law (halakha), especially in terms of what is religiously permitted, required, or prohibited.
-
E.
statusInRabbinicLiterature
Indicates how a person, concept, or text is regarded, classified, or treated within rabbinic literature and tradition.
- 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c812e2f481909d90451f25013476 |
completed | May 3, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.