Triple
T36406617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Церковь Святого Архангела Михаила |
E896763
|
entity |
| Predicate | связана с почитанием |
P152948
|
FINISHED |
| Object | небесные силы |
—
|
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: небесные силы | Statement: [Церковь Святого Архангела Михаила, связана с почитанием, небесные силы]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: связана с почитанием Context triple: [Церковь Святого Архангела Михаила, связана с почитанием, небесные силы]
-
A.
повʼязанеЗ
chosen
Indicates a general association or connection between one entity and another.
-
B.
связан с персонажами
Indicates that something has a connection or association with certain characters.
-
C.
associatedWithSee
Indicates a relationship where one entity is contextually or functionally linked to another through the act or concept of seeing or visual observation.
-
D.
relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
-
E.
readingOf
Indicates that one entity is an interpretation, measurement, or recorded value derived from another 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_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.