Triple
T24402988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surrender |
E615229
|
entity |
| Predicate | originalComposerOfSource |
P93691
|
FINISHED |
| Object | Ernesto De Curtis |
—
|
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: Ernesto De Curtis | Statement: [Surrender, originalComposerOfSource, Ernesto De Curtis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalComposerOfSource Context triple: [Surrender, originalComposerOfSource, Ernesto De Curtis]
-
A.
originalArtistOfSourceWork
Indicates that one entity is the artist who created the original source work from which another work is derived or adapted.
-
B.
originalAuthorOfSource
Indicates that an entity is the original creator or author of a given source or work.
-
C.
composerOfSourceWork
chosen
Indicates that an entity is the composer who created the original source work on which another work is based.
-
D.
originalArtistOfComponents
Indicates that an entity is the original creator or artist responsible for the component parts of another composite or assembled entity.
-
E.
hasUnknownOriginalComposer
Indicates that the work’s original composer is not known or cannot be identified.
- 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_69e2d7e780bc81908049c779e697a7f6 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f294dc1240819085aba9a8c2e07f42 |
completed | April 29, 2026, 11:31 p.m. |
| PD | Predicate disambiguation | batch_69f287c4a2b48190b80fb7a3c0e9b018 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:05 a.m.