Triple
T2161665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulgarian Greek Catholic Church |
E46813
|
entity |
| Predicate | hasEthnicCharacter |
P27835
|
FINISHED |
| Object | Bulgarian |
—
|
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: Bulgarian | Statement: [Bulgarian Greek Catholic Church, hasEthnicCharacter, Bulgarian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEthnicCharacter Context triple: [Bulgarian Greek Catholic Church, hasEthnicCharacter, Bulgarian]
-
A.
hasEthnicCharacteristic
chosen
Indicates that an entity possesses or is associated with a particular ethnic characteristic or identity.
-
B.
protagonistEthnicity
Indicates the ethnic background or cultural heritage associated with a work’s main character.
-
C.
spokenByEthnicGroup
Indicates that a particular language, dialect, or speech variety is used or spoken by a specified ethnic group.
-
D.
involvedEthnicGroup
Indicates that a particular ethnic group participates in, is affected by, or is otherwise associated with the referenced event, situation, or entity.
-
E.
otherEthnicGroup
Indicates that one entity belongs to a different ethnic group than the other 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_69a88a184cbc8190877791f6552c2484 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe89e6ac8190b4b4bc0be4fe7aa9 |
completed | March 7, 2026, 5:58 a.m. |
| PD | Predicate disambiguation | batch_69abbd9c90408190b6b65498ca43ce26 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.