Triple
T20606936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carl Lerner |
E506333
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Boomerang! |
—
|
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: Boomerang! | Statement: [Carl Lerner, workedOn, Boomerang!]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boomerang! Context triple: [Carl Lerner, workedOn, Boomerang!]
-
A.
Boomerang!
chosen
Boomerang! is a 1947 American film noir crime drama noted for its semi-documentary style and exploration of a real-life wrongful murder accusation.
-
B.
Boomerang
Boomerang is a steel shuttle roller coaster known for its forward-and-backward looping layout, operating at the Worlds of Fun amusement park in Kansas City, Missouri.
-
C.
Boomerang
"Boomerang" is a 2015 French drama film directed by François Favrat, in which François Cluzet stars in a story about a man uncovering long-buried family secrets.
-
D.
Boomerang
The Boomerang is an unconventional twin-boom, asymmetric light aircraft designed by Burt Rutan to offer improved safety and performance compared to traditional twin-engine planes.
-
E.
Boomerang
Boomerang is a television network known for airing classic and contemporary animated programming, particularly cartoons from the Warner Bros. and Hanna-Barbera libraries.
- 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_69e0b4bb2b4081908fa4a72444120f35 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aad394e8819080185187a8b3de93 |
completed | April 20, 2026, 10:38 p.m. |
Created at: April 16, 2026, 11:41 a.m.