Triple
T21324970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate Levering |
E525727
|
entity |
| Predicate | characterRole |
P268
|
FINISHED |
| Object | Kim Kaswell |
—
|
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: Kim Kaswell | Statement: [Kate Levering, characterRole, Kim Kaswell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Kaswell Context triple: [Kate Levering, characterRole, Kim Kaswell]
-
A.
Kim Kaswell
chosen
Kim Kaswell is a driven, sharp-tongued attorney on the legal dramedy series "Drop Dead Diva," known for her ambition, wit, and complicated relationships with her colleagues.
-
B.
Shanley Caswell
Shanley Caswell is an American actress best known for her role as Andrea Perron in the supernatural horror film "The Conjuring."
-
C.
Kassie Larson
Kassie Larson is a central character in the romantic comedy film "The Switch," whose unexpected pregnancy via artificial insemination sets off the movie’s main emotional and comedic events.
-
D.
Kari Keegan
Kari Keegan is an American actress best known for her role in the horror film "Jason Goes to Hell: The Final Friday."
-
E.
Kelli Rhoads
Kelli Rhoads is a musician best known for her association with the American glam metal band Ratt.
- 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_69e0b51b90788190a4dd823d962626da |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e77ed7732c8190a0e7aec6e7cbcef2 |
completed | April 21, 2026, 1:42 p.m. |
Created at: April 16, 2026, 4:41 p.m.