Triple
T22484746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Breathes |
E555849
|
entity |
| Predicate | hasCoverArtBy |
P5936
|
FINISHED |
| Object | David Welker |
—
|
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: David Welker | Statement: [Billy Breathes, hasCoverArtBy, David Welker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Welker Context triple: [Billy Breathes, hasCoverArtBy, David Welker]
-
A.
David Welker
chosen
David Welker is an American artist and illustrator best known for his intricate, surreal concert posters and album artwork, particularly associated with bands like Phish.
-
B.
David Kahne
David Kahne is an American record producer and engineer known for his work with major artists across rock and pop, including Paul McCartney.
-
C.
Michael Lerner
Michael Lerner was an American character actor known for his prolific film and television career, including an Academy Award–nominated role in "Barton Fink."
-
D.
Bob Tzudiker
Bob Tzudiker is an American screenwriter best known for co-writing Disney animated films such as "Tarzan" and "The Lion King."
-
E.
Dan Seymour
Dan Seymour was an American character actor known for his frequent portrayals of villains and ethnic heavies in classic Hollywood films and television during the mid-20th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c3bb8cc8190950efd84ebe86b73 |
completed | April 29, 2026, 1:17 a.m. |
Created at: April 16, 2026, 8:49 p.m.