Triple
T30574159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Сатин |
E778197
|
entity |
| Predicate | являетсяПерсонажемПроизведения |
P110595
|
FINISHED |
| Object | «На дне» |
—
|
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: «На дне» | Statement: [Сатин, являетсяПерсонажемПроизведения, «На дне»]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: являетсяПерсонажемПроизведения Context triple: [Сатин, являетсяПерсонажемПроизведения, «На дне»]
-
A.
characterInBookBy
chosen
Indicates that a character appears in a book that was written by a specified author.
-
B.
literaryCharacterModeledAs
Indicates that one literary character is created or portrayed based on the traits, life, or persona of another real or fictional individual.
-
C.
characterInWorkDescribedAs
Indicates that a character is portrayed or described in a particular way within a specific work.
-
D.
genreOfWorkCharacterIsIn
Indicates the specific genre of the creative work in which a given character appears.
-
E.
fictionalCharacterAssociatedWith
Indicates that there is a notable connection or association between a fictional character and another entity, such as a work, creator, or universe.
- 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_69f2249f8c148190ae7eb3912cde112a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f689167878819093cb4f58efd47e2e |
completed | May 2, 2026, 11:30 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:22 p.m.