Triple
T28331842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La jolie fille de Perth |
E717555
|
entity |
| Predicate | followedByWorkOfComposer |
P181652
|
FINISHED |
| Object | Djamileh |
—
|
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: Djamileh | Statement: [La jolie fille de Perth, followedByWorkOfComposer, Djamileh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followedByWorkOfComposer Context triple: [La jolie fille de Perth, followedByWorkOfComposer, Djamileh]
-
A.
followedByInComposerWork
Indicates that one element in a composer's work directly succeeds another in sequence within that same composition.
-
B.
followedByInVerdiOeuvre
Indicates that one work in Verdi’s oeuvre is immediately succeeded by another in the chronological sequence of his compositions.
-
C.
isRelatedWorkOfComposer
Indicates that one work is associated with or connected to a particular composer, typically as a composition created by that composer.
-
D.
precededByInComposerWork
Indicates that one element in a composer's work occurs earlier in the sequence than another element within the same composition.
-
E.
hasComposerPreviousWork
Indicates that a composer has created an earlier work prior to the current one.
- 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f7805ce6208190ac6dbd9c97989978 |
completed | May 3, 2026, 5:05 p.m. |
| PD | Predicate disambiguation | batch_69f77956ec648190ba4fb7e9d83fd107 |
completed | May 3, 2026, 4:35 p.m. |
| PDg | Predicate description generation | batch_69f7805c25dc8190b9977c561ba15975 |
completed | May 3, 2026, 5:05 p.m. |
Created at: April 28, 2026, 12:32 a.m.