Triple
T24989165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | نظامی گنجوی |
E625401
|
entity |
| Predicate | جزء خمسه |
P157511
|
FINISHED |
| Object | خسرو و شیرین |
E384955
|
NE 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: خسرو و شیرین | Statement: [نظامی گنجوی, جزء خمسه, خسرو و شیرین]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: جزء خمسه Context triple: [نظامی گنجوی, جزء خمسه, خسرو و شیرین]
-
A.
جزء خمسه
chosen
Indicates that something constitutes one-fifth (a fifth part) of something else.
-
B.
الجيل
Indicates a generational relationship, linking entities as belonging to the same generation or specifying that one entity is a particular generation relative to another.
-
C.
عدد المقاطع
Indicates the number of segments or parts into which something is divided.
-
D.
عدد الحروف
Indicates the relationship that specifies the number of letters contained in a given word or text.
-
E.
التأثير
Indicates a relationship where one entity produces a change or has an influence on another entity or its state.
- F. None of above.
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_69e2ff2611c081908710457fbe6d376b |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1048a96d608190a01f1c1476525b69 |
completed | May 22, 2026, 12:14 p.m. |
| PD | Predicate disambiguation | batch_69f44d77f6e88190a4643ab2cbef567b |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:03 a.m.