Triple
T24133746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | АН СССР |
E598024
|
entity |
| Predicate | структурнаяЕдиница |
P135717
|
FINISHED |
| Object | отделения по отраслям наук |
—
|
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: отделения по отраслям наук | Statement: [АН СССР, структурнаяЕдиница, отделения по отраслям наук]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: структурнаяЕдиница Context triple: [АН СССР, структурнаяЕдиница, отделения по отраслям наук]
-
A.
containsStructuralUnit
chosen
Indicates that one entity includes or encompasses another entity as a structural subunit or component within its overall structure.
-
B.
typeOfUnitStructure
Indicates that one unit is classified as having a particular structural type or organizational form.
-
C.
hasUnitStructure
Indicates that an entity possesses a specific internal organization or arrangement that defines its structural composition.
-
D.
integratedStructure
Indicates that multiple components are combined into a single, cohesive structure that functions as an integrated whole.
-
E.
componentUnit
Indicates that one entity functions as a constituent or sub-unit that forms part of a larger composite entity.
- 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_69e288c92e448190ac57034fa0c863ce |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1df79bfd08190970ed1b3f14ebc8b |
completed | April 29, 2026, 10:37 a.m. |
| PD | Predicate disambiguation | batch_69f1765650fc8190a6bc1eb512b240bf |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:26 p.m.