Triple
T36406616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Церковь Святого Архангела Михаила |
E896763
|
entity |
| Predicate | относится к типу посвящения |
P36403
|
FINISHED |
| Object | архангельский храм |
—
|
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: архангельский храм | Statement: [Церковь Святого Архангела Михаила, относится к типу посвящения, архангельский храм]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: относится к типу посвящения Context triple: [Церковь Святого Архангела Михаила, относится к типу посвящения, архангельский храм]
-
A.
dedicationType
chosen
Indicates the specific kind or category of dedication that characterizes the relationship or action between entities.
-
B.
typeOfTribute
Indicates the specific kind or category of tribute that is being given or required in a relationship.
-
C.
isDevotedTo
Indicates a strong, enduring commitment or dedication that one entity directs toward another.
-
D.
dedicatedToStyleOf
Indicates that something is devoted or specifically tailored to a particular style or manner of expression.
-
E.
dedicatedToConcept
Indicates that something is specifically devoted, committed, or purposefully directed toward a particular concept or abstract idea.
- 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_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b91fd88190ab85afd626603769 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:10 p.m.