Triple
T8676627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miroirs |
E205930
|
entity |
| Predicate | hasOrchestralVersion |
P53545
|
FINISHED |
| Object | Une barque sur l’océan |
—
|
LITERAL FINISHED |
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: Une barque sur l’océan | Statement: [Miroirs, hasOrchestralVersion, Une barque sur l’océan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOrchestralVersion Context triple: [Miroirs, hasOrchestralVersion, Une barque sur l’océan]
-
A.
hasOrchestralFeature
Indicates that something includes, exhibits, or is characterized by a notable orchestral element or component.
-
B.
hasOrchestralSuite
chosen
Indicates that a musical work is associated with, or has been arranged into, an orchestral suite derived from it.
-
C.
hasAcousticVersionBy
Indicates that one entity is an acoustic version of another, created or performed by a specified agent.
-
D.
performedWithOrchestra
Indicates that a performance or musical work was carried out in collaboration with an orchestra.
-
E.
hasKaraokeVersion
Indicates that an entity has a corresponding karaoke (instrumental or sing-along) version of itself.
- 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_69ca83529a9c8190b5c075b4f14636ed |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4ae6d19c8190be003f7901c0468d |
completed | March 31, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69cc4567b5c881908d9ec5dcfc783fac |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:32 p.m.