Triple
T36862960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyiv–Halych |
E910992
|
entity |
| Predicate | principalSeeOf |
P186728
|
FINISHED |
| Object | Ukrainian Greek Catholic Church |
—
|
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: Ukrainian Greek Catholic Church | Statement: [Kyiv–Halych, principalSeeOf, Ukrainian Greek Catholic Church]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: principalSeeOf Context triple: [Kyiv–Halych, principalSeeOf, Ukrainian Greek Catholic Church]
-
A.
principalAct
Indicates that an entity performs or is responsible for the main or primary action in a given context.
-
B.
principalKamiOf
Indicates that one entity serves as the primary or chief kami (deity/spirit) associated with another entity, such as a place, shrine, or group.
-
C.
principalActFor
Indicates that one entity performs an action or enters into an arrangement on behalf of another entity in the capacity of a principal.
-
D.
principalPart
Indicates that one entity is the primary or most important component, role, or participant within the context defined by the other entity.
-
E.
principalModelOf
Indicates that one entity serves as the primary or main model or representation upon which another related entity is based or derived.
- F. None of above. chosen
Provenance (4 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_69f76e80f6f0819091cba8e19b269615 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
| PDg | Predicate description generation | batch_69fa0a799b9081909bfa8293a22c4b00 |
completed | May 5, 2026, 3:19 p.m. |
Created at: May 3, 2026, 4:13 p.m.