Triple
T21656908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Совет глав правительств ШОС |
E534490
|
entity |
| Predicate | состав |
P143902
|
FINISHED |
| Object | главы правительств 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: главы правительств государств-членов ШОС | Statement: [Совет глав правительств ШОС, состав, главы правительств государств-членов ШОС]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: состав Context triple: [Совет глав правительств ШОС, состав, главы правительств государств-членов ШОС]
-
A.
composéDe
chosen
Indicates that something is made up of, or consists of, one or more constituent parts.
-
B.
partOfComposition
Indicates that one entity is a component, section, or constituent element within a larger composite whole represented by another entity.
-
C.
specialComposition
Indicates that one entity is composed of another in a distinctive or non-standard way, highlighting a particular or exceptional form of composition between them.
-
D.
featuresCompositionBy
Indicates that something includes or presents a composition created by a particular composer or creator.
-
E.
compositionForm
Indicates the structural or organizational form in which something is composed or arranged.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5919c9c88190a2ddcf2cefee79a5 |
completed | April 27, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e696826c3c81909270791e79760937 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:36 p.m.