Triple
T33937948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | المدرسة النحوية البصرية |
E870085
|
entity |
| Predicate | تُنسَب_إلى |
P37
|
FINISHED |
| Object | مدينة البصرة |
—
|
NE NERFINISHED |
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: مدينة البصرة | Statement: [المدرسة النحوية البصرية, تُنسَب_إلى, مدينة البصرة]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: تُنسَب_إلى Context triple: [المدرسة النحوية البصرية, تُنسَب_إلى, مدينة البصرة]
-
A.
повʼязанеЗ
Indicates a general association or connection between one entity and another.
-
B.
relatedToTerm
Indicates a general, non-specific relationship or association between one term and another.
-
C.
relatedTo
chosen
Indicates a general, non-specific relationship or association exists between two entities.
-
D.
trägtBeiZu
Indicates that one entity contributes to, promotes, or plays a role in bringing about a certain state, effect, or outcome in another.
-
E.
tiedTo
Indicates that one entity is physically or figuratively fastened, bound, or otherwise constrained in connection to another entity.
- 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_69f3499a59788190bff762a891471b31 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.