Triple
T32389687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Белая Троицкая церковь |
E827634
|
entity |
| Predicate | основное посвящение |
P24360
|
FINISHED |
| Object | Святая Троица |
—
|
NE NERFINISHED |
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: Святая Троица | Statement: [Белая Троицкая церковь, основное посвящение, Святая Троица]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: основное посвящение Context triple: [Белая Троицкая церковь, основное посвящение, Святая Троица]
-
A.
dedicatee
chosen
Indicates the person or entity to whom a work, such as a book, artwork, or performance, is formally dedicated.
-
B.
inspiredDedicationOf
Indicates that one entity’s dedication, commitment, or devoted effort is motivated, sparked, or strengthened by another entity.
-
C.
dedicationType
Indicates the specific kind or category of dedication that characterizes the relationship or action between entities.
-
D.
usedAsDedicationFor
Indicates that something (such as a work, object, or act) is dedicated in honor of, or specifically intended for, another entity.
-
E.
dedicationBy
Indicates that one entity formally dedicates, commits, or devotes another entity (such as a work, resource, or effort) to a particular person, purpose, or cause.
- 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_69f349184e7481909c6c54428cb9cf12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c1d48d048190b6bb79e26881adb7 |
completed | May 3, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:52 a.m.