Triple
T36406627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Церковь Святого Архангела Михаила |
E896763
|
entity |
| Predicate | имеет архитектурный тип |
P63910
|
FINISHED |
| Object | церковь |
—
|
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: церковь | Statement: [Церковь Святого Архангела Михаила, имеет архитектурный тип, церковь]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: имеет архитектурный тип Context triple: [Церковь Святого Архангела Михаила, имеет архитектурный тип, церковь]
-
A.
hasArchType
chosen
Indicates that one entity possesses or is characterized by a particular architectural type or style.
-
B.
hasArchitectureBy
Indicates that an entity’s architectural design was created or authored by a specified architect or architectural firm.
-
C.
architectInstanceOf
Indicates that an architect is an instance or specific example of a more general architect class or type.
-
D.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an entity.
-
E.
hasArchitecturalPlanType
Indicates that an entity has or is associated with a specific type or category of architectural plan.
- 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:10 p.m.