Triple
T22184774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marguerite Charpentier |
E548264
|
entity |
| Predicate | portraitMedium |
P93180
|
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: [Marguerite Charpentier, portraitMedium, oil on canvas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraitMedium Context triple: [Marguerite Charpentier, portraitMedium, oil on canvas]
-
A.
imageMedium
chosen
Indicates the medium or format through which an image is created or presented (e.g., painting, photograph, digital).
-
B.
portraitOn
Indicates that one entity is depicted as a portrait on the surface or medium of another entity.
-
C.
subjectMedium
Indicates the medium or channel through which the subject is expressed, communicated, or realized.
-
D.
mediumDepictedIn
Indicates that a particular medium or material is represented, shown, or referenced within another work or depiction.
-
E.
portraitSpecialization
Indicates that one entity specializes in creating or working with portraits, distinguishing a focused area of expertise within a broader artistic or professional domain.
- 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_69f12aa823888190829368de6db4aa91 |
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.