Triple
T13967783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | self-portrait of Caravaggio as a lantern-bearing figure |
E335970
|
entity |
| Predicate | mediumOfContainingWork |
P99077
|
FINISHED |
| Object | oil on canvas |
—
|
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: oil on canvas | Statement: [self-portrait of Caravaggio as a lantern-bearing figure, mediumOfContainingWork, oil on canvas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediumOfContainingWork Context triple: [self-portrait of Caravaggio as a lantern-bearing figure, mediumOfContainingWork, oil on canvas]
-
A.
mediumOfWorkAppearsIn
chosen
Indicates that a particular medium or format is the form in which a work is presented or appears.
-
B.
mediumOfFame
Indicates the medium, field, or domain through which an entity became famous or gained public recognition.
-
C.
mediumOfAcademicWork
Indicates that a particular medium or format is the channel through which an academic work is expressed, recorded, or communicated.
-
D.
notableWorkContained
Indicates that a notable work is included within or is part of another entity, such as a collection, publication, or compilation.
-
E.
exhibitionMedium
Indicates the material or format through which something is exhibited or displayed.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e8c9e988190a84c9ca8a78b515f |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69dd465a21408190b912a42c50ffa0d9 |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:18 p.m.