Triple
T27750905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atelier du Midi |
E702108
|
entity |
| Predicate | conceptualCenter |
P128794
|
FINISHED |
| Object | The Yellow House in Arles |
—
|
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: The Yellow House in Arles | Statement: [Atelier du Midi, conceptualCenter, The Yellow House in Arles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conceptualCenter Context triple: [Atelier du Midi, conceptualCenter, The Yellow House in Arles]
-
A.
centerIs
Indicates that one entity serves as the central point or middle position of another entity or space.
-
B.
conceptualAspect
chosen
Indicates that one entity represents an abstract, conceptual, or non-physical aspect, feature, or dimension of another entity.
-
C.
formsCenterOf
Indicates that one entity constitutes the central or core part of another entity.
-
D.
isConceptual
Indicates that something exists as an abstract or theoretical idea rather than as a concrete, physical entity.
-
E.
centerOfOrigin
Indicates the place or region where something (such as a species, product, idea, or movement) originally began or was first developed.
- 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_69ef6a53c7388190899baa6daf42301c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f69383222c81909d8baa04129d5c81 |
completed | May 3, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f690eb1e948190aab41a89969519a5 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 27, 2026, 4:20 p.m.