Triple
T157200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Good Shepherd |
E3204
|
entity |
| Predicate | iconographicTypeOf |
P3050
|
FINISHED |
| Object | Jesus depicted carrying a lamb |
—
|
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: Jesus depicted carrying a lamb | Statement: [Good Shepherd, iconographicTypeOf, Jesus depicted carrying a lamb]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iconographicTypeOf Context triple: [Good Shepherd, iconographicTypeOf, Jesus depicted carrying a lamb]
-
A.
artworkType
chosen
Indicates the specific category or kind of artwork that characterizes the relationship between the subject and the artwork.
-
B.
isInscribedOn
Indicates that text, symbols, or markings are written, carved, or otherwise permanently placed onto the surface of an object.
-
C.
exhibitionType
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
-
D.
hasIllustrationsBy
Indicates that one entity (such as a work or publication) includes illustrations that were created by another entity (the illustrator).
-
E.
hasTypeOfInsignia
Indicates that an entity bears or is associated with a specific kind or category of insignia.
- 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a25830136881909f5ecb2cb22097b2 |
completed | Feb. 28, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69a2565f30848190a2a71fdb7dc140b5 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.