Triple
T7593634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grande Galerie |
E179799
|
entity |
| Predicate | housedCollection |
P8906
|
FINISHED |
| Object | Italian paintings |
—
|
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: Italian paintings | Statement: [Grande Galerie, housedCollection, Italian paintings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: housedCollection Context triple: [Grande Galerie, housedCollection, Italian paintings]
-
A.
housesCollection
chosen
Indicates that one entity serves as a container or repository that holds or stores a collection of other entities.
-
B.
housedWorkBy
Indicates that one entity serves as the location or repository where a work created by another entity is kept or displayed.
-
C.
housedInCountry
Indicates that an entity is located, based, or situated within the boundaries of a specified country.
-
D.
collectionBuiltAround
Indicates that a collection is organized, structured, or conceptually centered around a particular core item, theme, or entity.
-
E.
museumHolds
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
- 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_69c69f3487ec8190bf7acdf2dd91e6d6 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f9bab3a08190a2c36b2c72a1de25 |
completed | March 27, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e2e42c8190afc802c4796c9cc2 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:53 p.m.