Triple
T23858184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amelia |
E592367
|
entity |
| Predicate | roleRequires |
P6843
|
FINISHED |
| Object | dramatic soprano voice |
—
|
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: dramatic soprano voice | Statement: [Amelia, roleRequires, dramatic soprano voice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleRequires Context triple: [Amelia, roleRequires, dramatic soprano voice]
-
A.
requiresRole
chosen
Indicates that performing an action or accessing a resource is contingent on the subject having a specified role or set of roles.
-
B.
roleDependsOn
Indicates that the existence, behavior, or permissions of one role are contingent upon or derived from another role.
-
C.
supportsRole
Indicates that one entity provides the necessary functionality, resources, or conditions for another entity to perform or occupy a specific role.
-
D.
roleWith
Indicates that one entity holds or performs a particular role in relation to another entity.
-
E.
hasRole
Indicates that an entity occupies, performs, or is assigned a specific role or function in relation to another entity or context.
- 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_69e25d22eb488190914b193aff952e83 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c98cad34819080baeb8f20f39741 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:12 p.m.