Triple
T24298863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | True Faith |
E606037
|
entity |
| Predicate | hasCoverVersionArtist |
P95695
|
FINISHED |
| Object | George Michael |
—
|
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: George Michael | Statement: [True Faith, hasCoverVersionArtist, George Michael]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoverVersionArtist Context triple: [True Faith, hasCoverVersionArtist, George Michael]
-
A.
hasCoverVersionPerformer
chosen
Indicates that an entity is the performer of a cover version of another entity’s original work.
-
B.
hasCoverVersionInGenre
Indicates that an entity has at least one cover version that is performed or produced within a specified musical genre.
-
C.
hasCoverVersions
Indicates that a musical work has one or more recorded versions performed or produced by artists other than the original creator.
-
D.
hasCoverVersionLanguage
Indicates that a cover version of a work is performed or produced in a specified language.
-
E.
hasCountryCoverVersionBy
Indicates that one entity is a country music cover version of another entity (typically an original song or recording).
- 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_69e29549335881909cbf27adcaba1cf0 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f2915c520081908055941209f35da5 |
completed | April 29, 2026, 11:16 p.m. |
| PD | Predicate disambiguation | batch_69f1c45c6ec081908401b69424428100 |
completed | April 29, 2026, 8:42 a.m. |
Created at: April 18, 2026, 12:09 a.m.