Triple
T28105947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poplars series paintings by Claude Monet |
E710361
|
entity |
| Predicate | someWorksHousedIn |
P32052
|
FINISHED |
| Object | Musée d’Orsay |
—
|
NE NERFINISHED |
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: Musée d’Orsay | Statement: [Poplars series paintings by Claude Monet, someWorksHousedIn, Musée d’Orsay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: someWorksHousedIn Context triple: [Poplars series paintings by Claude Monet, someWorksHousedIn, Musée d’Orsay]
-
A.
artCollectionHeldAt
Indicates that an art collection is housed, displayed, or maintained at a particular location or institution.
-
B.
exhibitsWorkOf
Indicates that one entity displays or presents the creative works produced by another entity.
-
C.
housedWorkBy
Indicates that one entity serves as the location or repository where a work created by another entity is kept or displayed.
-
D.
museumHolds
chosen
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
-
E.
hasExhibitsFrom
Indicates a relationship where one entity (typically a venue or collection) includes or displays exhibits originating from another entity (such as an artist, institution, or location).
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f64095680c8190a220f9345db8688d |
completed | May 2, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9:08 p.m.