Triple
T23923541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | אברהם אבן עזרא |
E602282
|
entity |
| Predicate | מאפיין פרשנות |
P154378
|
FINISHED |
| Object | דגש על פשט הכתוב |
—
|
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: דגש על פשט הכתוב | Statement: [אברהם אבן עזרא, מאפיין פרשנות, דגש על פשט הכתוב]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: מאפיין פרשנות Context triple: [אברהם אבן עזרא, מאפיין פרשנות, דגש על פשט הכתוב]
-
A.
מאפיין עונתי
Indicates that something exhibits a seasonal characteristic, pattern, or variation over time.
-
B.
מאפיין לוח
Indicates a relationship where something serves as a characteristic, property, or defining feature of a board.
-
C.
حكم تلاوتها
Indicates the ruling or legal judgment regarding the recitation of something (e.g., whether its recitation is obligatory, recommended, permissible, disliked, or forbidden).
-
D.
مصحفياً
Indicates that someone is acting in the capacity of a Qur’an specialist or is engaged in work related to the writing, editing, or production of the Qur’anic text.
-
E.
סיבת זכייה
Indicates the reason or cause for which an entity wins or is awarded something.
- F. None of above. chosen
Provenance (4 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_69e2953b928c819095395fa87baca583 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf1abd148190a8393418ed965019 |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f16e348b548190b76e50f9b611f76d |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 8:41 p.m.