Triple
T29706955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piano Sonata No. 3 in F minor, Op. 14 |
E751657
|
entity |
| Predicate | hasMainKey |
P200046
|
FINISHED |
| Object | F minor |
—
|
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: F minor | Statement: [Piano Sonata No. 3 in F minor, Op. 14, hasMainKey, F minor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainKey Context triple: [Piano Sonata No. 3 in F minor, Op. 14, hasMainKey, F minor]
-
A.
hasMainSubjectKey
Indicates that an entity is associated with a primary or principal subject identifier used as its main reference or key.
-
B.
hasMainSymbol
Indicates that one entity is designated as the primary or most representative symbol associated with another entity.
-
C.
hasMainElements
Indicates that something possesses or is composed of its primary or most important constituent parts.
-
D.
hasPrimary
Indicates that one entity is designated as the main or most important instance (the primary) in relation to another entity.
-
E.
hasMainKeepType
Indicates the specific type or category of main keep associated with a structure or site.
- 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_69f0d62748848190b030d0a703629a7d |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ff6ef0d61c81909162d37c15a1a3c3 |
completed | May 9, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69ff6c6a58e08190921317062cd9d489 |
completed | May 9, 2026, 5:18 p.m. |
| PDg | Predicate description generation | batch_69ff6eefa9c48190aac36916990f6db5 |
completed | May 9, 2026, 5:29 p.m. |
Created at: April 28, 2026, 7:28 p.m.