Triple
T6530468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thyssen-Bornemisza family |
E152216
|
entity |
| Predicate | knownForCollectionType |
P338
|
FINISHED |
| Object | Old Master 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: Old Master paintings | Statement: [Thyssen-Bornemisza family, knownForCollectionType, Old Master paintings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knownForCollectionType Context triple: [Thyssen-Bornemisza family, knownForCollectionType, Old Master paintings]
-
A.
knownForCollectionOf
Indicates that one entity is recognized or notable specifically for its collection or assemblage of another type of entity.
-
B.
hasCollectionType
chosen
Indicates that an entity is associated with or organized under a specific type or category of collection.
-
C.
isCollectionOf
Indicates that one entity is a group or aggregate composed of multiple instances or elements of another entity.
-
D.
overseesCollectionType
Indicates that one entity has responsibility for supervising, managing, or administering a particular type or category of collection.
-
E.
hasCollectionDedicatedTo
Indicates that one entity maintains a collection specifically devoted or dedicated to another entity.
- 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_69c688048ec8819093a47f7d332e12ec |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6adac53b0819097fece48a75cc48f |
completed | March 27, 2026, 4:17 p.m. |
| PD | Predicate disambiguation | batch_69c68abd9c7c819099e4fe8097cd1b28 |
completed | March 27, 2026, 1:48 p.m. |
Created at: March 27, 2026, 1:46 p.m.