Triple
T18755369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rounders |
E458634
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | David Levien |
—
|
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: David Levien | Statement: [Rounders, writer, David Levien]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Levien Context triple: [Rounders, writer, David Levien]
-
A.
David Levien
chosen
David Levien is an American screenwriter, novelist, and producer best known for co-writing crime and heist films as well as co-creating the television series "Billions."
-
B.
Jeff Levine
Jeff Levine is a film producer best known for his work on the horror drama "Shadow of the Vampire."
-
C.
Stephen Levy
Stephen Levy is a writer best known in this context as the author of the story that inspired the film "Kalifornia."
-
D.
Jonathan Levien
Jonathan Levien is the namesake of Levien Gymnasium, likely a significant benefactor or figure associated with the institution that houses the arena.
-
E.
Ken F. Levin
Ken F. Levin is a television and film producer best known for his executive production work on the hit superhero series "The Boys."
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579f084208190a4b3563d47154e69 |
completed | April 20, 2026, 12:57 a.m. |
Created at: April 10, 2026, 11:51 a.m.