Triple
T5578993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Bellows |
E146592
|
entity |
| Predicate | notableWorkTheme |
P4941
|
FINISHED |
| Object | boxing |
—
|
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: boxing | Statement: [George Bellows, notableWorkTheme, boxing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableWorkTheme Context triple: [George Bellows, notableWorkTheme, boxing]
-
A.
notableTheme
Indicates that a particular theme is prominently featured in, or strongly associated with, an entity such as a work, event, or body of content.
-
B.
notableWorkSubject
chosen
Indicates that a work is notably associated with a particular subject, such as a person, topic, or entity, as its primary focus or theme.
-
C.
notableWorkAspect
Indicates a specific characteristic, feature, or component that is a significant or defining part of a notable work.
-
D.
notableTypeOfWork
Indicates that a work is a significant or defining example within a particular type or category of work associated with an entity.
-
E.
notableWork
Indicates that one entity is a significant or well-known work (such as a book, artwork, or creation) produced by 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_69c0090287a08190b4098411effe970c |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0206bfea08190aa2c8df9f88013ac |
completed | March 22, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69c01b147cc081909237f3f2967d4cb8 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:37 p.m.