Triple
T37611831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romanze in F major, Op. 118 No. 5 |
E935802
|
entity |
| Predicate | hasExpressiveMarkings |
P151768
|
FINISHED |
| Object | cantabile |
—
|
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: cantabile | Statement: [Romanze in F major, Op. 118 No. 5, hasExpressiveMarkings, cantabile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExpressiveMarkings Context triple: [Romanze in F major, Op. 118 No. 5, hasExpressiveMarkings, cantabile]
-
A.
hasExpressiveCharacter
chosen
Indicates that something possesses a distinctive, emotionally or stylistically expressive quality or character.
-
B.
hasExpressivity
Indicates that one entity possesses a certain level or type of expressive power, capability, or richness in representation relative to another.
-
C.
hasFieldMarkingsFor
Indicates that one entity includes or displays field markings that are intended or suitable for use by another entity.
-
D.
hasExpressiveRole
Indicates that an entity serves a communicative or expressive function or role in relation to another entity or context.
-
E.
isExpressiveCharacter
Indicates that a character displays emotions, intentions, or personality in a vivid, noticeable, and communicative way.
- 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_69f76ed0a85481909254a8a89090c826 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: May 3, 2026, 4:18 p.m.