Triple
T21567640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Хартия ШОС |
E532202
|
entity |
| Predicate | закрепляет |
P144276
|
FINISHED |
| Object | основные направления сотрудничества государств-членов ШОС |
—
|
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: основные направления сотрудничества государств-членов ШОС | Statement: [Хартия ШОС, закрепляет, основные направления сотрудничества государств-членов ШОС]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: закрепляет Context triple: [Хартия ШОС, закрепляет, основные направления сотрудничества государств-членов ШОС]
-
A.
binding
Indicates that one entity physically or chemically attaches, adheres, or forms a stable association with another entity.
-
B.
tightens
Indicates that one entity makes another entity more secure, compact, or taut by applying constricting force or reducing looseness.
-
C.
fixation
Indicates an intense, often obsessive focus or attachment of one entity toward another entity, object, or idea.
-
D.
closure
Indicates that an entity is closed or not accessible/available for use, entry, or interaction.
-
E.
closureBy
Indicates that one entity causes, performs, or is responsible for the closing or termination of another entity, event, or process.
- F. None of above. chosen
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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9c9f264819085b4807923860793 |
completed | April 27, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69e6320c8c2c81908bf031447d66a052 |
completed | April 20, 2026, 2:02 p.m. |
| PDg | Predicate description generation | batch_69e633bf34c481909925d8dc1a633a65 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 16, 2026, 6:30 p.m.