Triple
T38388543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ibéria |
E899644
|
entity |
| Predicate | hasMovementTitle2 |
P40263
|
FINISHED |
| Object | Les parfums de la nuit |
—
|
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: Les parfums de la nuit | Statement: [Ibéria, hasMovementTitle2, Les parfums de la nuit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMovementTitle2 Context triple: [Ibéria, hasMovementTitle2, Les parfums de la nuit]
-
A.
movement2Title
Indicates a relationship where a specific movement, action, or motion is associated with or labeled by a particular title or name.
-
B.
hasMovementWithProgrammaticTitle
Indicates that a musical work includes a movement whose title is programmatically descriptive (i.e., suggests a narrative, scene, or extra-musical idea).
-
C.
movement1Title
Indicates the title or descriptive label assigned to a specific movement within a larger work or sequence.
-
D.
haveMovementFor
Indicates that an entity exhibits or is assigned a specific type or pattern of movement in relation to another entity or context.
-
E.
secondMovementTitle
chosen
Indicates the title or name given to the second movement of a multi-movement musical 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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffc704e1e88190884928a6a5c55a87 |
completed | May 9, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69ffc6b483d881908ad872e25fa6abc5 |
completed | May 9, 2026, 11:43 p.m. |
Created at: May 3, 2026, 4:31 p.m.