Triple
T30691602
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Александр Николаевич Бенуа |
E781340
|
entity |
| Predicate | основная область деятельности |
P40655
|
FINISHED |
| Object | изобразительное искусство |
—
|
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: изобразительное искусство | Statement: [Александр Николаевич Бенуа, основная область деятельности, изобразительное искусство]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: основная область деятельности Context triple: [Александр Николаевич Бенуа, основная область деятельности, изобразительное искусство]
-
A.
primaryBusinessArea
Indicates the main field, sector, or domain in which an entity primarily conducts its business activities.
-
B.
регионДеятельности
Indicates the geographic region or area in which an entity carries out its activities or operations.
-
C.
placeOfBusinessActivity
Indicates the type or nature of business activity that is conducted at a particular place or location.
-
D.
majorActivity
chosen
Indicates that the related entity performs, participates in, or is primarily associated with a main or most significant activity.
-
E.
主な業態
Indicates the primary type or main form of business operation that characterizes an entity’s activities.
- 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_69f224ab24e08190991d6edb6df58e8b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68b8875ac8190bcd509983fb51b01 |
completed | May 2, 2026, 11:40 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:33 p.m.