Triple
T36406643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Церковь Святого Архангела Михаила |
E896763
|
entity |
| Predicate | может иметь духовенство |
P9815
|
FINISHED |
| Object | православный священник |
—
|
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: православный священник | Statement: [Церковь Святого Архангела Михаила, может иметь духовенство, православный священник]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: может иметь духовенство Context triple: [Церковь Святого Архангела Михаила, может иметь духовенство, православный священник]
-
A.
hasClergy
chosen
Indicates that an organization or institution possesses or is served by members of the clergy.
-
B.
hasClergyType
Indicates the specific category or role of clergy associated with an entity.
-
C.
hasClergyCharacter
Indicates that an entity possesses a religious or clerical role, status, or character.
-
D.
hasClergyOrder
Indicates that an entity is associated with, or belongs to, a specific religious or clerical order.
-
E.
mayBelongToDenomination
Indicates that an entity is possibly, but not certainly, affiliated with or a member of a particular denomination.
- 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_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf769338819092a5f42653dcc956 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:10 p.m.