Triple
T37312804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bily Clocks Museum |
E926248
|
entity |
| Predicate | creatorOfCollection |
P57973
|
FINISHED |
| Object | Frank Bily |
—
|
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: Frank Bily | Statement: [Bily Clocks Museum, creatorOfCollection, Frank Bily]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creatorOfCollection Context triple: [Bily Clocks Museum, creatorOfCollection, Frank Bily]
-
A.
creatorOfWorkInCollection
Indicates that one entity is the creator of a work that is included within a particular collection.
-
B.
collectedBy
Indicates that one entity has gathered, acquired, or assembled another entity, typically as part of a collection or data-gathering process.
-
C.
creatorOfGroup
chosen
Indicates that one entity is the originator or founder responsible for creating a particular group.
-
D.
creatorMember
Indicates that an entity is a member who created or originally authored another entity (such as a work, item, or resource).
-
E.
creatorType
Indicates the role or category of a creator in relation to the creation of something (e.g., author, artist, director).
- 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_69f76eb28af88190b093b32e3fd614ab |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffe613c03481909f3043ec8bf0bed9 |
completed | May 10, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69ffe4a73fb4819091600725a443981a |
completed | May 10, 2026, 1:51 a.m. |
Created at: May 3, 2026, 4:16 p.m.