Triple
T28221459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Paul Gachet |
E711467
|
entity |
| Predicate | artCollectionIncludes |
P17367
|
FINISHED |
| Object | works by Paul Cézanne |
—
|
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: works by Paul Cézanne | Statement: [Dr. Paul Gachet, artCollectionIncludes, works by Paul Cézanne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artCollectionIncludes Context triple: [Dr. Paul Gachet, artCollectionIncludes, works by Paul Cézanne]
-
A.
artCollectionHeldAt
Indicates that an art collection is housed, displayed, or maintained at a particular location or institution.
-
B.
artCollectionFocus
Indicates that an art collection is primarily centered around or devoted to a particular theme, style, period, subject, or type of artwork.
-
C.
artCollectionLaterHeldBy
Indicates that an art collection was initially owned or assembled by one party and subsequently came to be held or possessed by another party at a later time.
-
D.
artIncludes
Indicates that a work of art contains, incorporates, or is composed of another artistic element or component.
-
E.
hasArtCollection
chosen
Indicates that an entity possesses, maintains, or is associated with a collection of artworks.
- 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_69efb51dfb048190ada79b745c33b363 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f64351ed64819097b557edd9fa37e1 |
completed | May 2, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 10:46 p.m.