Triple
T25121173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Bannatyne |
E629269
|
entity |
| Predicate | collectionContainsWorksBy |
P111604
|
FINISHED |
| Object | William Dunbar |
—
|
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: William Dunbar | Statement: [George Bannatyne, collectionContainsWorksBy, William Dunbar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectionContainsWorksBy Context triple: [George Bannatyne, collectionContainsWorksBy, William Dunbar]
-
A.
containsWorksFrom
chosen
Indicates that one entity includes or holds works that originate from or are created by another entity.
-
B.
hasArtworksFrom
Indicates that one entity possesses or includes artworks that originate from or are created by another entity.
-
C.
creatorOfWorkInCollection
Indicates that one entity is the creator of a work that is included within a particular collection.
-
D.
worksCollectedBy
Indicates that one entity gathers, compiles, or curates the works (such as creations, publications, or outputs) produced by another entity.
-
E.
worksWithArtist
Indicates that one entity collaborates or engages in professional work with an artist.
- 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_69e2ff3288048190bd82c3b7f7bd0e62 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f606c79ad081908369605f72e65ca6 |
completed | May 2, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_69f602ce79ec8190b8336c2b9de18ac7 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 18, 2026, 6:28 a.m.