Triple
T23290720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Want My Wife Back |
E590021
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Ben Miller |
—
|
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: Ben Miller | Statement: [I Want My Wife Back, leadActor, Ben Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ben Miller Context triple: [I Want My Wife Back, leadActor, Ben Miller]
-
A.
Ben Miller
Ben Miller is a former Special Forces operative turned mercenary in the action thriller film "Triple Frontier," known for his tactical skills and loyalty to his team.
-
B.
Ben Miller
chosen
Ben Miller is a British actor and comedian best known as one half of the comedy duo Armstrong and Miller and for roles in series such as "Death in Paradise" and "Primeval."
-
C.
Chris Mills
Chris Mills is a former American professional basketball player who played as a forward in the NBA during the 1990s and early 2000s.
-
D.
Will Miller
Will Miller is an American business executive best known as a member of the influential Miller family behind Cummins Inc. and a leader in corporate and civic affairs.
-
E.
Matthew Downey
Matthew Downey is an individual associated with or making use of something referred to as "Downey," though publicly available distinguishing information about him is limited.
- 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_69e25d1af9d88190a0b9b5e8fa608618 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196cb3fec8190a95255da97dd984e |
completed | April 29, 2026, 5:27 a.m. |
Created at: April 17, 2026, 5:01 p.m.