Triple
T31031593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pénélope |
E790741
|
entity |
| Predicate | hasWorkComposer |
P118009
|
FINISHED |
| Object | Michel Legrand |
—
|
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: Michel Legrand | Statement: [Pénélope, hasWorkComposer, Michel Legrand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkComposer Context triple: [Pénélope, hasWorkComposer, Michel Legrand]
-
A.
hasWorkCreator
chosen
Indicates that an entity is the creator or originator of a particular work (such as a document, artwork, or other creative product).
-
B.
hasCoComposer
Indicates that an entity shares authorship of a musical composition with one or more other composers.
-
C.
hasComposerPreviousWork
Indicates that a composer has created an earlier work prior to the current one.
-
D.
hasWorkBy
Indicates that one entity (such as a collection, exhibition, or publication) includes or contains creative works produced by another entity (such as an artist, author, or creator).
-
E.
basedOnWorkComposer
Indicates that one work is derived from, adapted from, or otherwise created on the basis of another work by the specified composer.
- 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_69f224c97a788190b5da1ead6038a74e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: April 29, 2026, 8:59 p.m.