Triple
T31076570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Happiest Girl in the World |
E791979
|
entity |
| Predicate | sourceComposer |
P110264
|
FINISHED |
| Object | Jacques Offenbach |
—
|
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: Jacques Offenbach | Statement: [The Happiest Girl in the World, sourceComposer, Jacques Offenbach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceComposer Context triple: [The Happiest Girl in the World, sourceComposer, Jacques Offenbach]
-
A.
sampleSourceComposer
chosen
Indicates that an entity is the composer or creator from which a given sample or excerpt is derived.
-
B.
composerSource
Indicates that one entity is the source or origin of the composer associated with another entity.
-
C.
dedicatedComposer
Indicates that one entity is a composer who is devoted or committed specifically to another entity or purpose.
-
D.
setComposer
Indicates that an entity assigns or specifies another entity as the composer of a work or item.
-
E.
supportedComposer
Indicates that one entity provided backing, resources, or advocacy that helped another entity (a composer) create, develop, or promote their musical work.
- 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_69f224ccdbbc81909b0cdb4cc2d70c7a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 29, 2026, 9:02 p.m.