Triple
T3170479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Carousel Waltz |
E66318
|
entity |
| Predicate | functionInWork |
P46726
|
FINISHED |
| Object | orchestral prelude |
—
|
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: orchestral prelude | Statement: [The Carousel Waltz, functionInWork, orchestral prelude]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionInWork Context triple: [The Carousel Waltz, functionInWork, orchestral prelude]
-
A.
functionInSystem
Indicates that an entity serves a specific role or performs a particular function within a given system.
-
B.
publicFunction
Indicates that a function or method is accessible from outside its defining scope, module, or class (i.e., it has public visibility).
-
C.
intendedFunction
Indicates that something is designed or purposed to perform a particular role, use, or function.
-
D.
workOn
Indicates that an agent is actively engaged in performing tasks or making progress on a particular project, object, or assignment.
-
E.
functionInName
Indicates that the name of one entity includes or references the function or role of another entity.
- F. None of above. chosen
Provenance (4 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada66c043081908eb23a4fe3420a78 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada20880e481908ecac09d49b1f1c3 |
completed | March 8, 2026, 4:21 p.m. |
Created at: March 8, 2026, 3:06 p.m.