Triple
T20517619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. Woodcock |
E503720
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Ethan Suplee |
—
|
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: Ethan Suplee | Statement: [Mr. Woodcock, starring, Ethan Suplee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ethan Suplee Context triple: [Mr. Woodcock, starring, Ethan Suplee]
-
A.
Ethan Suplee
chosen
Ethan Suplee is an American actor known for his roles in films like "Remember the Titans" and "Mallrats" and the TV series "My Name Is Earl."
-
B.
Ethan Cutkosky
Ethan Cutkosky is an American actor best known for playing Carl Gallagher on the U.S. version of the television series "Shameless."
-
C.
Nathan Tyson
Nathan Tyson is an English professional footballer known as a pacey forward who has played for numerous clubs in the English Football League.
-
D.
Ethan Anka
Ethan Anka is a member of the Anka family, known primarily as the son of legendary singer-songwriter Paul Anka and brother of actress Amanda Anka.
-
E.
Christopher Fennell
Christopher Fennell is an actor known for his role in the film "The War."
- 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_69e0b4b2aa788190ae9eb37c1d73b1f1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69f42db688190a3ccfba5601e8bf3 |
completed | April 20, 2026, 9:48 p.m. |
Created at: April 16, 2026, 11:36 a.m.