Triple
T20390945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Species |
E498081
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Michael Madsen |
—
|
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: Michael Madsen | Statement: [Species, castMember, Michael Madsen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Madsen Context triple: [Species, castMember, Michael Madsen]
-
A.
Michael Madsen
chosen
Michael Madsen is an American actor known for his tough-guy roles in films such as Reservoir Dogs, Kill Bill, and other Quentin Tarantino movies.
-
B.
Charles Bronson
Charles Bronson was an American film actor best known for his tough-guy roles in action and Western movies, including the "Death Wish" series.
-
C.
Armand Assante
Armand Assante is an American actor known for his intense screen presence and roles in crime dramas and historical films.
-
D.
Cole Hauser
Cole Hauser is an American actor known for his tough, authoritative roles in films like "Dazed and Confused," "Pitch Black," and "2 Fast 2 Furious," as well as the TV series "Yellowstone."
-
E.
Jack Curtis
Jack Curtis was an early 20th-century American actor known for his roles in silent films, including the crime drama "Turn to the Right."
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790f8d9c819093038f6bb6f47a92 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.