Triple
T21441394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crimes of Passion |
E528946
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Keith Olsen |
—
|
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: Keith Olsen | Statement: [Crimes of Passion, producer, Keith Olsen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keith Olsen Context triple: [Crimes of Passion, producer, Keith Olsen]
-
A.
Keith Olsen
chosen
Keith Olsen was an American record producer and sound engineer renowned for his work with major rock and pop artists from the 1970s onward, including Fleetwood Mac, Ozzy Osbourne, and Pat Benatar.
-
B.
Ben Olsen
Ben Olsen is a former American soccer player and coach best known for his long association with D.C. United in Major League Soccer.
-
C.
Mike Olson
Mike Olson is a technology entrepreneur best known as a co-founder and former chief strategy officer of the big data software company Cloudera.
-
D.
Phil Olsen
Phil Olsen is a former American football defensive lineman who played in the NFL, notably for the Los Angeles Rams, and is the younger brother of Hall of Famer Merlin Olsen.
-
E.
Ken Ralston
Ken Ralston is an acclaimed visual effects supervisor known for his groundbreaking work on major films such as the Star Wars and Back to the Future series.
- 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_69e0c4569fa081908101baa24f8745db |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b7022a5081908d9ad5058cecb8e5 |
completed | April 22, 2026, 11:54 a.m. |
Created at: April 16, 2026, 6:05 p.m.