Triple
T24003920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madonna of the Goldfinch |
E594319
|
entity |
| Predicate | depictionOfJohnTheBaptist |
P1852
|
FINISHED |
| Object | kneeling infant John the Baptist |
—
|
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: kneeling infant John the Baptist | Statement: [Madonna of the Goldfinch, depictionOfJohnTheBaptist, kneeling infant John the Baptist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictionOfJohnTheBaptist Context triple: [Madonna of the Goldfinch, depictionOfJohnTheBaptist, kneeling infant John the Baptist]
-
A.
viewOfJohnTheBaptist
Indicates a perspective, depiction, or representation specifically concerning John the Baptist.
-
B.
JohnTheBaptistReaction
Indicates John the Baptist’s response, attitude, or behavior in reaction to a particular event, message, or person.
-
C.
depictsPerson
chosen
Indicates that one entity visually represents or portrays a specific person.
-
D.
depictsSacrament
Indicates that one entity visually represents or portrays a religious sacrament associated with another entity.
-
E.
depictsApostlesAs
Indicates how a subject visually represents or portrays apostles in an image, artwork, or depiction.
- 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_69e288b9ecf08190b8c94a278f5674fe |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d467108481909e33de1c7319738a |
completed | April 29, 2026, 9:50 a.m. |
| PD | Predicate disambiguation | batch_69f17639d23c8190bed93434e2f9230a |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:40 p.m.