Triple
T34371147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | premio Sonzogno for Cavalleria rusticana |
E882157
|
entity |
| Predicate | workAwardedForm |
P16784
|
FINISHED |
| Object | one-act opera |
—
|
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: one-act opera | Statement: [premio Sonzogno for Cavalleria rusticana, workAwardedForm, one-act opera]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workAwardedForm Context triple: [premio Sonzogno for Cavalleria rusticana, workAwardedForm, one-act opera]
-
A.
awardForm
chosen
Indicates that one entity is the specific form, type, or category of an award associated with another entity.
-
B.
awardedForWorkOn
Indicates that one entity grants an award or recognition to another entity specifically for that entity’s work on a particular project, task, or subject.
-
C.
awardedFrom
Indicates that one entity has received an award, prize, or honor that originates from or is granted by another entity.
-
D.
awardFor
Indicates that something is given or granted as recognition or a prize for a particular achievement, work, or contribution.
-
E.
awardTo
Indicates that an award, prize, or honor is given or assigned to a particular recipient.
- 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_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:59 a.m.