Triple
T38599471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiordiligi |
E934168
|
entity |
| Predicate | operaStructureContext |
P88989
|
FINISHED |
| Object | major role across all three acts |
—
|
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: major role across all three acts | Statement: [Fiordiligi, operaStructureContext, major role across all three acts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operaStructureContext Context triple: [Fiordiligi, operaStructureContext, major role across all three acts]
-
A.
operaStructureRole
chosen
Indicates the functional or narrative role that a structural element plays within an opera.
-
B.
operaPremiereContext
Indicates the circumstances or setting (such as time, place, or event) in which an opera had its premiere performance.
-
C.
operaComponent
Indicates that one entity is a constituent part or section of an opera associated with the other entity.
-
D.
operaForm
Indicates that one entity is a specific form, style, or structural type of opera in relation to another entity.
-
E.
stateStructureContext
Indicates the contextual framework or structural conditions of a state within which a given relationship or action occurs.
- 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_69f76ecc17688190b389b693a5927501 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a2026248190b894436a578d79ac |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.