Triple
T19972928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giverny artist colony |
E480122
|
entity |
| Predicate | artisticActivities |
P108084
|
FINISHED |
| Object | plein-air painting |
—
|
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: plein-air painting | Statement: [Giverny artist colony, artisticActivities, plein-air painting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artisticActivities Context triple: [Giverny artist colony, artisticActivities, plein-air painting]
-
A.
hasArtisticActivity
chosen
Indicates that an entity engages in, participates in, or is associated with an artistic activity or creative practice.
-
B.
artisticField
Indicates the artistic domain or creative discipline in which an entity is active or associated.
-
C.
artisticTraining
Indicates that one entity has provided, received, or been involved in formal or informal instruction or education in the arts from or with another entity.
-
D.
artisticAmbition
Indicates a desire or drive to create, achieve, or excel in artistic or creative pursuits.
-
E.
artisticMedium
Indicates the material or technique used to create an artwork or artistic expression.
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65bca94c0819095c902a411c4c4b8 |
completed | April 20, 2026, 5 p.m. |
| PD | Predicate disambiguation | batch_69e537fae79c81909eae39500766d0b6 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:54 p.m.