Triple
T29483659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | الوحي الإلهي المنزل على النبي محمد صلى الله عليه وسلم |
E747859
|
entity |
| Predicate | أول ما نزل |
P110168
|
FINISHED |
| Object | سورة العلق من الآية 1 إلى 5 |
—
|
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: سورة العلق من الآية 1 إلى 5 | Statement: [الوحي الإلهي المنزل على النبي محمد صلى الله عليه وسلم, أول ما نزل, سورة العلق من الآية 1 إلى 5]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: أول ما نزل Context triple: [الوحي الإلهي المنزل على النبي محمد صلى الله عليه وسلم, أول ما نزل, سورة العلق من الآية 1 إلى 5]
-
A.
نزلت_قبل
chosen
Indicates that one entity descended, arrived, or was released earlier in time than another entity.
-
B.
نزلت في
Indicates that an entity arrived at, stayed in, or lodged at a particular place.
-
C.
سبب النزول
Indicates the relationship of being the specific cause, event, or circumstance that led to the revelation of a particular Quranic verse or passage.
-
D.
بداية المنصب
Indicates the starting point in time when an entity officially assumes a position or office.
-
E.
من حيث النزول
Indicates the relationship of a text to its place or context of revelation or descent (e.g., where or in what circumstances it was revealed).
- 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_69f0bd43ba30819095eb1cfc3adf525c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66bdbc7e88190a5fe93938d0cdc7c |
completed | May 2, 2026, 9:25 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:06 p.m.