Triple
T10369621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franz Mayer |
E244344
|
entity |
| Predicate | typeOfCollector |
P81528
|
FINISHED |
| Object | decorative arts collector |
—
|
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: decorative arts collector | Statement: [Franz Mayer, typeOfCollector, decorative arts collector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfCollector Context triple: [Franz Mayer, typeOfCollector, decorative arts collector]
-
A.
hasCollector
Indicates that an entity is associated with, or owned/curated by, a specific collector.
-
B.
associatedWithCollector
chosen
Indicates that an entity has a relationship or connection with a collector, such as being owned, managed, or handled by that collector.
-
C.
overseesCollectionType
Indicates that one entity has responsibility for supervising, managing, or administering a particular type or category of collection.
-
D.
colliderType
Indicates the type or category of physical collision behavior defined for an object in a simulation or physics system.
-
E.
usesGarbageCollectorType
Indicates that one entity employs or is configured to employ a specific type of garbage collection mechanism or strategy associated with 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9725fa08190816bedf0acefbc2a |
completed | April 7, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69d4dface5508190a7b42f01ad0a19a2 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 12:01 p.m.