Triple
T22891068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epic (2013 film) |
E568040
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Daniel Shere |
—
|
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: Daniel Shere | Statement: [Epic (2013 film), screenwriter, Daniel Shere]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daniel Shere Context triple: [Epic (2013 film), screenwriter, Daniel Shere]
-
A.
Daniel Shere
chosen
Daniel Shere is a screenwriter best known for his work on the animated film "Epic."
-
B.
David Sherwin
David Sherwin was a British screenwriter best known for co-writing the influential 1968 film "If...." directed by Lindsay Anderson.
-
C.
Fabrice Sapolsky
Fabrice Sapolsky is a French comic book writer, editor, and publisher best known for co-creating the Marvel Comics character Spider-Man Noir.
-
D.
Michael Levine
Michael Levine is a prominent American developmental and molecular biologist known for his influential research on gene regulation and for coauthoring major genetics textbooks.
-
E.
Michael Levine
Michael Levine is the brother of Maroon 5 lead singer and television personality Adam Levine.
- 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f17fc59e108190a22f90c2439830fb |
completed | April 29, 2026, 3:49 a.m. |
Created at: April 17, 2026, 3:40 p.m.