Triple
T6141905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kastoria |
E136980
|
entity |
| Predicate | hasReligiousBuildingStyle |
P69416
|
FINISHED |
| Object | Byzantine church architecture |
—
|
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: Byzantine church architecture | Statement: [Kastoria, hasReligiousBuildingStyle, Byzantine church architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReligiousBuildingStyle Context triple: [Kastoria, hasReligiousBuildingStyle, Byzantine church architecture]
-
A.
hasCathedralStyle
Indicates that something possesses or is characterized by a particular architectural style associated with a cathedral.
-
B.
hasReligiousInstitutionType
Indicates that an entity is associated with, or classified by, a specific type of religious institution.
-
C.
hasCathedralType
Indicates that an entity is associated with, classified by, or designated as having a specific type or category of cathedral.
-
D.
religiousBuildingDesigned
Indicates that one entity (typically an architect or designer) is responsible for designing a religious building associated with the other entity.
-
E.
hasChapelStyle
Indicates that a chapel possesses or is characterized by a particular architectural or stylistic design.
- 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_69c008a2c6308190a56519b22d55d083 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05cb387ac8190a60579b59a741425 |
completed | March 22, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69c055f19b0c81908be34a00ab218723 |
completed | March 22, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69c056c87340819088003f427706ebf8 |
completed | March 22, 2026, 8:53 p.m. |
Created at: March 22, 2026, 4:16 p.m.