Triple
T37611853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intermezzo, Op. 118 No. 1 |
E935803
|
entity |
| Predicate | dedicatedWithSetTo |
P1283
|
FINISHED |
| Object | Clara Schumann |
—
|
NE NERFINISHED |
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: Clara Schumann | Statement: [Intermezzo, Op. 118 No. 1, dedicatedWithSetTo, Clara Schumann]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dedicatedWithSetTo Context triple: [Intermezzo, Op. 118 No. 1, dedicatedWithSetTo, Clara Schumann]
-
A.
dedicatedWithCycleTo
Indicates that something is allocated or reserved for a particular purpose or entity in a way that involves or depends on a recurring cycle or periodic process.
-
B.
dedicated
chosen
Indicates that one entity is formally assigned, reserved, or committed for the specific use, benefit, or purpose of another entity.
-
C.
dedicatedInstrument
Indicates that one entity serves as a specific, exclusive instrument or tool used for the purposes of another entity or activity.
-
D.
dedicatedToDomain
Indicates that something is specifically designed, intended, or reserved for use within a particular domain or area of application.
-
E.
rededicatedBy
Indicates that something has been dedicated again or anew by a particular agent or entity.
- 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_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.