Triple
T17955476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beethoven’s ten violin sonatas |
E448933
|
entity |
| Predicate | keyRange |
P28992
|
FINISHED |
| Object | various major and minor keys |
—
|
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: various major and minor keys | Statement: [Beethoven’s ten violin sonatas, keyRange, various major and minor keys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyRange Context triple: [Beethoven’s ten violin sonatas, keyRange, various major and minor keys]
-
A.
keySpace
Indicates the logical namespace or partition within a data store or system in which a particular key or set of keys is defined and managed.
-
B.
rangeOf
chosen
Indicates that one entity specifies the set of possible values (range) that another entity’s outputs or properties can take.
-
C.
keySpaceSize
Indicates the total number of distinct keys that can exist within a given key space or key domain.
-
D.
keyValue
Indicates that one entity functions as a key that is associated with a corresponding value represented by the other entity.
-
E.
rangeType
Indicates the type or category of values that can appear in the range (output) position of a property or relation.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afafe814819085300163f73de5f2 |
completed | April 19, 2026, 10:34 a.m. |
| PD | Predicate disambiguation | batch_69e3f8f2bd088190b1e22ad4d9cc8b13 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.