Triple
T29576424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Violin Concerto |
E753455
|
entity |
| Predicate | subtitleTranslation |
P58041
|
FINISHED |
| Object | To the Memory of an Angel |
—
|
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: To the Memory of an Angel | Statement: [Violin Concerto, subtitleTranslation, To the Memory of an Angel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subtitleTranslation Context triple: [Violin Concerto, subtitleTranslation, To the Memory of an Angel]
-
A.
subtitle
Indicates that one work serves as a secondary or explanatory title to another, typically appearing beneath the main title.
-
B.
subtitleDFunction
Indicates a functional relationship where one entity serves as the subtitle or secondary textual label for another entity.
-
C.
translationTitle
chosen
Indicates that one entity is the title assigned to a translated version of another entity (such as a work, document, or text).
-
D.
translationHint
Indicates that one entity provides guidance or suggestions on how another entity should be translated into a different language.
-
E.
translatedIn
Indicates that a work, text, or content has been rendered from its original language into another specified language or linguistic form.
- 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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66d4b7f848190b6af93ae829a5caa |
completed | May 2, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:03 p.m.