Triple
T22021106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Made |
E543848
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Doug Davison |
—
|
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: Doug Davison | Statement: [American Made, producer, Doug Davison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Doug Davison Context triple: [American Made, producer, Doug Davison]
-
A.
Doug Davison
chosen
Doug Davison is a film and television producer known for working on major Hollywood projects such as "The Lake House."
-
B.
Scott Davidson
Scott Davidson was a New York City firefighter who died in the September 11, 2001 attacks and is known as the late father of comedian Pete Davidson.
-
C.
Austin Corbett
Austin Corbett is an American football offensive lineman who played college football at Nevada and went on to a professional career in the NFL.
-
D.
Jason Jessup
Jason Jessup is a central murder suspect whose retrial drives the legal suspense in Michael Connelly’s novel "The Reversal."
-
E.
Mitch Seavey
Mitch Seavey is an American dog musher best known as a multiple-time Iditarod Trail Sled Dog Race champion from Alaska.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c7b3308190ac056bef6f82722e |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:23 p.m.