Triple
T3163062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Timurid miniature painting |
E66145
|
entity |
| Predicate | commonSubject |
P32595
|
FINISHED |
| Object | scenes from the Shahnameh |
—
|
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: scenes from the Shahnameh | Statement: [Timurid miniature painting, commonSubject, scenes from the Shahnameh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonSubject Context triple: [Timurid miniature painting, commonSubject, scenes from the Shahnameh]
-
A.
commonIn
Indicates that something frequently occurs, appears, or is found within a specified context, group, or environment.
-
B.
commonsCategory
Indicates that an entity is associated with a specific media or topic category on Wikimedia Commons.
-
C.
commonFor
chosen
Indicates that something is typical, usual, or frequently occurring for a given entity or context.
-
D.
commonCut
Indicates that two or more entities share at least one identical segment or portion that has been cut or divided in the same way.
-
E.
commonMedium
Indicates that two or more entities share the same medium or channel through which interaction, communication, or transmission occurs.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada61a4b8481908897a8d39d94c2f4 |
completed | March 8, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfe0a948190928f2201d671c654 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.