Triple
T21722344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lost in Hollywood |
E536190
|
entity |
| Predicate | keyboardist |
P12601
|
FINISHED |
| Object | Don Airey |
—
|
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: Don Airey | Statement: [Lost in Hollywood, keyboardist, Don Airey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don Airey Context triple: [Lost in Hollywood, keyboardist, Don Airey]
-
A.
Don Airey
chosen
Don Airey is an English rock keyboardist best known for his work with Deep Purple and numerous other prominent hard rock and heavy metal acts.
-
B.
Joe Tonahill
Joe Tonahill was an American defense attorney best known for serving on the legal team that defended Jack Ruby after Ruby killed Lee Harvey Oswald.
-
C.
Byron McLaughlin
Byron McLaughlin is a former American Major League Baseball pitcher who played primarily for the Seattle Mariners in the late 1970s and early 1980s.
-
D.
Glen Leach
Glen Leach is a musician best known as a member of the British rock band Wishbone Ash.
-
E.
Rob Couhig
Rob Couhig is an American businessman and lawyer known for owning and leading English football club Wycombe Wanderers.
- 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_69e0c46c6dd88190a595375fa6ebd701 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efd97032c08190820b87a288e77293 |
completed | April 27, 2026, 9:47 p.m. |
Created at: April 16, 2026, 6:47 p.m.