Triple
T38201160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shame, Shame, Shame |
E1009060
|
entity |
| Predicate | albumOfCoverVersion |
P65373
|
FINISHED |
| Object | Honkin' on Bobo |
—
|
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: Honkin' on Bobo | Statement: [Shame, Shame, Shame, albumOfCoverVersion, Honkin' on Bobo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: albumOfCoverVersion Context triple: [Shame, Shame, Shame, albumOfCoverVersion, Honkin' on Bobo]
-
A.
coverVersionAlbumType
Indicates that an album is a cover version type, meaning its recordings are reinterpretations of previously released works rather than original material.
-
B.
coverOfArtist
Indicates that one entity is a cover version of a musical work originally performed or recorded by the specified artist.
-
C.
notableCoverAlbum
chosen
Indicates that one entity is a notable album consisting primarily of cover versions of songs originally by another entity.
-
D.
albumRecorded
Indicates that a musical album was recorded by a particular artist, group, or at a specific place or time.
-
E.
albumEdition
Indicates a specific version or release variant of an album, often distinguished by features such as format, bonus content, packaging, or region.
- 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_69f76dc94fcc8190bd2f55e81f9d6527 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcc42cbac48190b8d3e4c9ce140838 |
completed | May 7, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fc69c88190800453eb57a7e62c |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:30 p.m.