Triple
T20624376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghosts of Download |
E506778
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Matt Katz-Bohen |
—
|
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: Matt Katz-Bohen | Statement: [Ghosts of Download, producer, Matt Katz-Bohen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Katz-Bohen Context triple: [Ghosts of Download, producer, Matt Katz-Bohen]
-
A.
Matt Katz-Bohen
chosen
Matt Katz-Bohen is an American musician, songwriter, and producer best known as a longtime keyboardist and collaborator with the band Blondie.
-
B.
Jason Katz
Jason Katz is an American screenwriter and story artist best known for his work on Pixar animated films.
-
C.
Todd Katzberg
Todd Katzberg is a television writer and producer best known for co-creating the CIA thriller series "Condor."
-
D.
Benji Kohn
Benji Kohn is a film producer best known for his work on the acclaimed documentary "A Band Called Death," which helped bring wider recognition to the pioneering proto-punk band Death.
-
E.
Brett Gelman
Brett Gelman is an American actor and comedian known for his eccentric, often darkly comic roles in television series such as "Stranger Things," "Fleabag," and various Adult Swim productions.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe3d76c8190a8a5cb52bb9bfc2b |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.