Triple
T19092977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Gadon |
E467333
|
entity |
| Predicate | hasWorkedWith |
P9615
|
FINISHED |
| Object | Drake Doremus |
—
|
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: Drake Doremus | Statement: [Sarah Gadon, hasWorkedWith, Drake Doremus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drake Doremus Context triple: [Sarah Gadon, hasWorkedWith, Drake Doremus]
-
A.
Drake Doremus
chosen
Drake Doremus is an American filmmaker known for his intimate, improvisation-driven romantic dramas, including the acclaimed film "Like Crazy."
-
B.
William H. Doremus
William H. Doremus was an American individual notable enough to be interred at Hackensack Cemetery in Hackensack, New Jersey.
-
C.
Jesse Eisenberg
Jesse Eisenberg is an American actor, playwright, and filmmaker best known for his Academy Award–nominated portrayal of Mark Zuckerberg in the film "The Social Network."
-
D.
Emile Hirsch
Emile Hirsch is an American actor known for his intense performances in films such as "Into the Wild," "Milk," and "Lone Survivor."
-
E.
David Doremus
David Doremus is an American former child actor best known for his role as Hal Everett on the early 1970s television sitcom "Nanny and the Professor."
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e34cf5e481908e1f180dacd5602f |
completed | April 20, 2026, 8:26 a.m. |
Created at: April 10, 2026, 12:04 p.m.