Triple
T20177029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Want to Be on TV |
E492626
|
entity |
| Predicate | performerRole |
P9616
|
FINISHED |
| Object | Tré Cool – drums |
—
|
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: Tré Cool – drums | Statement: [I Want to Be on TV, performerRole, Tré Cool – drums]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tré Cool – drums Context triple: [I Want to Be on TV, performerRole, Tré Cool – drums]
-
A.
Tré Cool – drums
Tré Cool – drums refers to Green Day’s longtime drummer Tré Cool performing the drum parts on the track “27th Ave. Shuffle.”
-
B.
Tré Cool
chosen
Tré Cool is the longtime drummer of the American punk rock band Green Day, known for his energetic playing style and stage presence.
-
C.
drums (Anton Fig)
Drums (Anton Fig) refers to the dynamic drumming style and performances of Anton Fig, best known as the longtime drummer for David Letterman’s house band, often called “The World’s Most Dangerous Band.”
-
D.
Curtis Crowe – drums
Curtis Crowe is the drummer for the influential Athens, Georgia post-punk band Pylon.
-
E.
Brian Downey (drummer)
Brian Downey is an Irish drummer best known as a founding member of the hard rock band Thin Lizzy.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668ec4d7c81909fa4bdc58ed54aeb |
completed | April 20, 2026, 5:57 p.m. |
Created at: April 11, 2026, 11:36 p.m.