Triple
T34854896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ляби-Хауз |
E1004701
|
entity |
| Predicate | архитектурныеЭлементы |
P5770
|
FINISHED |
| Object | айваны |
—
|
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: айваны | Statement: [Ляби-Хауз, архитектурныеЭлементы, айваны]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: архитектурныеЭлементы Context triple: [Ляби-Хауз, архитектурныеЭлементы, айваны]
-
A.
architecturalConcept
chosen
Indicates that one entity represents or embodies an architectural concept in relation to another entity.
-
B.
architecturalWork
Indicates that one entity is an architectural creation (such as a building or structure) designed or realized by another entity.
-
C.
architecturalSymbol
Indicates that one entity serves as a symbolic or emblematic representation of another within an architectural context.
-
D.
toArchitecture
Indicates a relationship in which something is designed, structured, or organized according to a particular architectural style, plan, or system.
-
E.
mainArchitecturalForm
Indicates the primary architectural style or structural form that characterizes a building or construction.
- 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_69f76dba76f0819090643cba102c41ec |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782f4f10081908f97f6d0d2dbeec7 |
completed | May 3, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69f780ff71cc8190a67e71076fbad81a |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.