Triple
T5342791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Legion (2010 film) |
E123981
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Kevin Durand |
E375629
|
NE FINISHED |
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: Kevin Durand | Statement: [Legion (2010 film), starring, Kevin Durand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Durand Context triple: [Legion (2010 film), starring, Kevin Durand]
-
A.
Kevin Durand
chosen
Kevin Durand is a Canadian character actor known for his imposing presence and roles in films and TV series such as "X-Men Origins: Wolverine," "The Strain," and "Lost."
-
B.
Thomas Jane
Thomas Jane is an American actor best known for his roles in films such as "The Punisher," "Deep Blue Sea," and "Boogie Nights," as well as the TV series "The Expanse."
-
C.
Lewis Pullman
Lewis Pullman is an American actor known for roles in films such as "Top Gun: Maverick," "Bad Times at the El Royale," and "The Strangers: Prey at Night."
-
D.
Geoffrey Wright
Geoffrey Wright is an Australian film director best known for his gritty and controversial work, including the neo-Nazi skinhead drama "Romper Stomper."
-
E.
Richard Gant
Richard Gant is an American character actor known for his roles in film and television, often portraying authoritative or tough-minded figures.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd464be27081908807b40b75c1bbae |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85cc5a9881909e23bf9c5b697a8e |
completed | March 20, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf21c5f82481908e9061d68c1e7496 |
completed | March 21, 2026, 10:55 p.m. |
Created at: March 20, 2026, 2:01 p.m.