Triple
T17944763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephen Moyer |
E448674
|
entity |
| Predicate | coStar |
P43875
|
FINISHED |
| Object | Ryan Kwanten |
—
|
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: Ryan Kwanten | Statement: [Stephen Moyer, coStar, Ryan Kwanten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ryan Kwanten Context triple: [Stephen Moyer, coStar, Ryan Kwanten]
-
A.
Ryan Kwanten
chosen
Ryan Kwanten is an Australian actor best known for playing Jason Stackhouse on the HBO vampire drama series "True Blood."
-
B.
Iain De Caestecker
Iain De Caestecker is a Scottish actor best known for his role as Leo Fitz in the Marvel television series "Agents of S.H.I.E.L.D."
-
C.
Max Thieriot
Max Thieriot is an American actor known for his roles in films like "Catch That Kid" and "House at the End of the Street," as well as television series such as "SEAL Team" and "Fire Country," which he also co-created.
-
D.
Aaron Johnson
Aaron Johnson is a musician best known for his past role as a member of the indie rock band Okkervil River.
-
E.
Aaron Johnson
Aaron Johnson is an English actor known for roles in films such as "Kick-Ass," "Nowhere Boy," and "Albert Nobbs."
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad9819a88190ad4ea7d562cf3f28 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 10:21 a.m.