Triple
T36665561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aural Oasis |
E905249
|
entity |
| Predicate | partOfNotableAlbum |
P130404
|
FINISHED |
| Object | Black Codes (From the Underground) |
—
|
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: Black Codes (From the Underground) | Statement: [Aural Oasis, partOfNotableAlbum, Black Codes (From the Underground)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfNotableAlbum Context triple: [Aural Oasis, partOfNotableAlbum, Black Codes (From the Underground)]
-
A.
hasPartInDiscography
Indicates that an entity (such as a song, album, or track) is included as a component within another entity’s discography.
-
B.
hasPartInDiscographyOf
chosen
Indicates that one entity constitutes a component or item within the discography (recorded works catalog) of another entity.
-
C.
partOfAlbumType
Indicates that one entity is a specific type or category of album to which the other entity belongs.
-
D.
includedInBestSellingAlbum
Indicates that an item (such as a song or track) is part of an album that is classified as a best-selling album.
-
E.
coveredOnAlbum
Indicates that a song or musical work has been recorded as a cover version and included on a particular album.
- 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a0123d1162c81908182d01ba3ddd236 |
completed | May 11, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_6a01236713d88190b12a567c0dfb2d49 |
completed | May 11, 2026, 12:31 a.m. |
Created at: May 3, 2026, 4:12 p.m.