Triple
T25083287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casilda |
E628242
|
entity |
| Predicate | composerOfWorkSheAppearsIn |
P99127
|
FINISHED |
| Object | Arthur Sullivan |
—
|
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: Arthur Sullivan | Statement: [Casilda, composerOfWorkSheAppearsIn, Arthur Sullivan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: composerOfWorkSheAppearsIn Context triple: [Casilda, composerOfWorkSheAppearsIn, Arthur Sullivan]
-
A.
composerOfWorkAppearsIn
chosen
Indicates that a person is the composer of a musical or artistic work that appears within another work or context.
-
B.
authorOfWorkHeAppearsIn
Indicates that a person is the author of a work in which he himself appears as a character or subject.
-
C.
genreOfWorkCharacterIsIn
Indicates the specific genre of the creative work in which a given character appears.
-
D.
appearsInWorkByTitle
Indicates that an entity appears in, is featured in, or is contained within a work identified by its title.
-
E.
appearsInWorkDirector
Indicates that an entity appears in a creative work in which the associated director is responsible for directing that work.
- 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_69e2ff2e73f881909992bf3eda5c25cb |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f55e519978819087a1676564a74630 |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f4a0edd10c81908a052ab864d57c54 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 18, 2026, 6:22 a.m.