Triple
T32866358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Kozelek |
E840658
|
entity |
| Predicate | notableCoverArtistOf |
P58280
|
FINISHED |
| Object | AC/DC |
E59220
|
NE 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: AC/DC | Statement: [Mark Kozelek, notableCoverArtistOf, AC/DC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCoverArtistOf Context triple: [Mark Kozelek, notableCoverArtistOf, AC/DC]
-
A.
hasNotableCoverArtist
Indicates that an entity has a cover (e.g., of a book, album, or publication) created by a cover artist who is considered notable.
-
B.
coverArtistOf
chosen
Indicates that one entity is the artist who created the cover artwork for another entity, such as a book, album, or publication.
-
C.
notableCover
Indicates that one entity is a particularly well-known or significant cover version or adaptation of another entity.
-
D.
comicArtistOfSource
Indicates that one entity is the comic artist responsible for creating the artwork for the specified source (such as a comic, issue, or publication).
-
E.
notableCoverGenre
Indicates that one entity is a genre in which another entity is notably covered, adapted, or reinterpreted.
- F. None of above.
Provenance (4 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_69f34942465c819099b3fb47f9044f58 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a34bd1311188190835de335975311b8 |
completed | June 19, 2026, 3:52 a.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:17 a.m.