Triple
T34371157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | premio Sonzogno for Cavalleria rusticana |
E882157
|
entity |
| Predicate | awardedWorkComposer |
P73785
|
FINISHED |
| Object | Pietro Mascagni |
—
|
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: Pietro Mascagni | Statement: [premio Sonzogno for Cavalleria rusticana, awardedWorkComposer, Pietro Mascagni]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: awardedWorkComposer Context triple: [premio Sonzogno for Cavalleria rusticana, awardedWorkComposer, Pietro Mascagni]
-
A.
dedicatedComposerWork
Indicates that a particular work was specifically created or formally dedicated by the composer to a person, group, or entity.
-
B.
workComposer
Indicates that one entity is the composer or creator of a musical or artistic work represented by the other entity.
-
C.
commissionedComposer
Indicates that one entity formally requested and funded another entity (a composer) to create a musical work.
-
D.
employedComposer
Indicates that one entity (such as a person or organization) employs another entity in the role of a composer.
-
E.
winnerComposer
chosen
Indicates that the subject is the composer who won a particular contest, award, or competitive event.
- 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_69f349bf5d7481908dd5da4cbdf74047 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: May 1, 2026, 1:59 a.m.