Triple
T22187182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holy Kinship |
E548324
|
entity |
| Predicate | visualCenter |
P130176
|
FINISHED |
| Object | grouping of Mary, Christ Child, and Saint Anne |
—
|
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: grouping of Mary, Christ Child, and Saint Anne | Statement: [Holy Kinship, visualCenter, grouping of Mary, Christ Child, and Saint Anne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualCenter Context triple: [Holy Kinship, visualCenter, grouping of Mary, Christ Child, and Saint Anne]
-
A.
visualCenterpiece
Indicates that one entity serves as the primary visual focus or dominant visual element in relation to another entity.
-
B.
sceneCenter
chosen
Indicates that one entity serves as the central or focal point of a scene in relation to another entity.
-
C.
centered
Indicates that one entity is positioned at or around the central point of another entity or reference frame.
-
D.
visualCompanion
Indicates that one entity serves as a visual counterpart, partner, or accompanying element to another in a visual context.
-
E.
visualDevice
Indicates a relationship where an entity functions as or is associated with a device used for visual display, capture, or processing.
- 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_69e11e3e0c7c8190b30d278845e2497e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aaa32288190830f6dfc626fb26a |
completed | April 28, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69e71b48576c8190a8e93738fd9cfda5 |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 8:35 p.m.