Triple
T15921097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunrise |
E386093
|
entity |
| Predicate | labelCataloguedIn |
P107050
|
FINISHED |
| Object | Blue Note discography |
—
|
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: Blue Note discography | Statement: [Sunrise, labelCataloguedIn, Blue Note discography]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: labelCataloguedIn Context triple: [Sunrise, labelCataloguedIn, Blue Note discography]
-
A.
labelCatalog
Indicates assigning or associating a descriptive label or identifier with a catalog entity or catalog entry.
-
B.
labelCatalogType
Indicates that an entity is assigned a specific catalog type label, defining its classification within a cataloging system.
-
C.
labelOf
Indicates that one entity serves as the name, tag, or identifying label assigned to another entity.
-
D.
catalogued as
chosen
Indicates that one entity has been recorded or registered under a specific identifier or entry within a catalog or systematic listing.
-
E.
labelIndication
Indicates that a label or designation is assigned to an entity to specify its indication, purpose, or intended use.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e172b48b308190bc430b2308cbc75b |
completed | April 16, 2026, 11:37 p.m. |
| PD | Predicate disambiguation | batch_69e142cf5c548190a931f7b58144cd31 |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:52 a.m.