Triple
T28209963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ذبیحالله مجاهد |
E711131
|
entity |
| Predicate | نقش ارتباطی |
P158182
|
FINISHED |
| Object | پل ارتباطی طالبان با رسانههای خارجی |
—
|
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: پل ارتباطی طالبان با رسانههای خارجی | Statement: [ذبیحالله مجاهد, نقش ارتباطی, پل ارتباطی طالبان با رسانههای خارجی]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: نقش ارتباطی Context triple: [ذبیحالله مجاهد, نقش ارتباطی, پل ارتباطی طالبان با رسانههای خارجی]
-
A.
مرتبطب
Indicates a relationship of being connected, associated, or related to something or someone.
-
B.
connectsRole
Indicates a relationship in which one entity is linked to another by assigning or associating a specific role between them.
-
C.
نمایاں_کردار
chosen
Indicates a relationship where an entity plays a prominent or significant role in relation to another entity or context.
-
D.
როლები
Indicates that an entity has specific roles, functions, or positions assigned or associated with it in a given context.
-
E.
ייחוס
Indicates an attribution or assignment relationship, where a property, role, or characteristic is ascribed from one entity to another.
- 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_69efb51cb5288190818c1f63a266af11 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f64310b67481908c2de1bc652d4d87 |
completed | May 2, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69f63c6c1a948190b68c0f92c264cc0c |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 10:38 p.m.