Triple
T25861019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | المذهب الحنبلي |
E651476
|
entity |
| Predicate | يقلل من |
P9925
|
FINISHED |
| Object | الاعتماد على الاستحسان |
—
|
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: الاعتماد على الاستحسان | Statement: [المذهب الحنبلي, يقلل من, الاعتماد على الاستحسان]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: يقلل من Context triple: [المذهب الحنبلي, يقلل من, الاعتماد على الاستحسان]
-
A.
reduces
chosen
Indicates that one entity causes a decrease in the amount, intensity, degree, or impact of another entity.
-
B.
decreasesWhen
Indicates that the value or intensity of one entity becomes lower as a result of changes in another entity or condition.
-
C.
minimizesRoleOf
Indicates that one entity reduces, downplays, or diminishes the importance, influence, or contribution of another entity’s role.
-
D.
decreedBy
Indicates that something (such as a rule, decision, or order) has been formally established or mandated by a particular authority or decision-making entity.
-
E.
reducedNumberOf
Indicates that the subject has a smaller quantity or count of the specified object or attribute compared to a prior state or reference level.
- 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_69e7ab3a199c81909227cb964cacfe24 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6026b467c8190a1f8be336f8679da |
completed | May 2, 2026, 1:55 p.m. |
| PD | Predicate disambiguation | batch_69f4939148dc81908706cec7d85291bc |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 8:05 a.m.