Triple
T112805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Talmud |
E2283
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Torah |
E7794
|
NE 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: Torah | Statement: [Talmud, basedOn, Torah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Torah Context triple: [Talmud, basedOn, Torah]
-
A.
Torah
chosen
The Torah is the central and most sacred text of Judaism, comprising the foundational five books that outline Jewish law, teachings, and early history.
-
B.
Tanakh
The Tanakh is the canonical collection of Hebrew scriptures that forms the foundational religious text of Judaism, encompassing the Torah (Law), Nevi'im (Prophets), and Ketuvim (Writings).
-
C.
Talmud
The Talmud is a central Jewish religious text comprising rabbinic discussions, legal rulings, and interpretations of the Hebrew Bible that form the foundation of traditional Jewish law and theology.
-
D.
Halakha
Halakha is the comprehensive body of traditional Jewish religious law and practice derived from the Torah, Talmud, and later rabbinic rulings.
-
E.
Siddur
The Siddur is the traditional Jewish prayer book containing the set order of daily, Shabbat, and holiday prayers used in Jewish worship.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a256eddd748190984a304000988a75 |
completed | Feb. 28, 2026, 2:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2b85e7e4881909322c67388d64247 |
completed | Feb. 28, 2026, 9:41 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.