Triple
T19647806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma (2019 film) |
E471726
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Luke Evans |
—
|
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: Luke Evans | Statement: [Ma (2019 film), castMember, Luke Evans]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luke Evans Context triple: [Ma (2019 film), castMember, Luke Evans]
-
A.
Luke Evans
chosen
Luke Evans is a Welsh actor and singer known for his roles in films such as "The Hobbit" trilogy, "Dracula Untold," and various high-profile Hollywood productions.
-
B.
Steve Kinnaman
Steve Kinnaman is the father of Swedish-American actor Joel Kinnaman.
-
C.
Justin Long
Justin Long is an American actor known for his comedic and romantic comedy roles in films like "Dodgeball," "Accepted," and the "I'm a Mac" Apple commercials.
-
D.
Daniel Gillies
Daniel Gillies is a New Zealand-Canadian actor and filmmaker best known for his roles in television series such as "The Vampire Diaries" and its spin-off "The Originals."
-
E.
Hal Courtney
Hal Courtney is a fictional 17th-century seafarer and adventurer who serves as the central hero of Wilbur Smith’s historical novel series, including "Monsoon."
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64126cea88190a1a6929f46de4686 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:44 p.m.