Triple
T1889603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Human Rights and Alliance of Civilizations Room |
E41838
|
entity |
| Predicate | artworkMedium |
P18308
|
FINISHED |
| Object | paint and resin on ceiling |
—
|
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: paint and resin on ceiling | Statement: [Human Rights and Alliance of Civilizations Room, artworkMedium, paint and resin on ceiling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artworkMedium Context triple: [Human Rights and Alliance of Civilizations Room, artworkMedium, paint and resin on ceiling]
-
A.
artisticMedium
chosen
Indicates the material or technique used to create an artwork or artistic expression.
-
B.
depictsMedium
Indicates that one entity visually represents or portrays the medium or material of another entity.
-
C.
artworkType
Indicates the specific category or kind of artwork that characterizes the relationship between the subject and the artwork.
-
D.
artworkBy
Indicates that one entity is the creator or artist responsible for producing the other entity as an artwork.
-
E.
artisticDepiction
Indicates that one entity visually represents, portrays, or illustrates another in an artistic medium.
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb142e41881908fc7335673a9dec3 |
completed | March 7, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69abafe61bc48190ac9ead027df930e1 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.