Triple
T37202284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liebster Jesu, hör mein Flehen, BWV Anh. 63 (attributed) |
E922071
|
entity |
| Predicate | possibleComposer |
P187659
|
FINISHED |
| Object | Johann Michael Bach |
—
|
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: Johann Michael Bach | Statement: [Liebster Jesu, hör mein Flehen, BWV Anh. 63 (attributed), possibleComposer, Johann Michael Bach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleComposer Context triple: [Liebster Jesu, hör mein Flehen, BWV Anh. 63 (attributed), possibleComposer, Johann Michael Bach]
-
A.
employedComposer
Indicates that one entity (such as a person or organization) employs another entity in the role of a composer.
-
B.
associatedComposerCatalog
Indicates a relationship between a work and a specific catalog of that composer’s works with which it is associated.
-
C.
regularComposer
Indicates that one entity habitually or consistently composes works for another entity, such as a publication, organization, or project.
-
D.
coComposer
Indicates a relationship where two or more entities jointly compose a musical or artistic work together.
-
E.
publishedComposer
Indicates that a composer has had their musical works formally published, typically by a recognized publisher or label.
- 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_69f76ea4849481909b4a3073efb0114c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb78cbef988190b8f79d946b46e6b2 |
completed | May 6, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9ac5a08190b24ef308963fc52b |
completed | May 6, 2026, 3:13 p.m. |
| PDg | Predicate description generation | batch_69fb78c982ac8190846efe8f6209e5d1 |
completed | May 6, 2026, 5:22 p.m. |
Created at: May 3, 2026, 4:15 p.m.