Triple
T20347339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Day After Tomorrow |
E495904
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Tamlyn Tomita |
—
|
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: Tamlyn Tomita | Statement: [The Day After Tomorrow, castMember, Tamlyn Tomita]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamlyn Tomita Context triple: [The Day After Tomorrow, castMember, Tamlyn Tomita]
-
A.
Tamlyn Tomita
chosen
Tamlyn Tomita is a Japanese-American actress best known for her breakout role in The Karate Kid Part II and her extensive work in film and television, including projects like The Joy Luck Club and The Man in the High Castle.
-
B.
Melissa Loya
Melissa Loya is known as the wife of Episcopal bishop Craig Loya.
-
C.
Kimberly Ann Vadala
Kimberly Ann Vadala is an American fitness model and instructor best known as the ex-wife of sports media personality Colin Cowherd.
-
D.
Lisa Gottsegen
Lisa Gottsegen is an American businesswoman and philanthropist best known as the longtime wife of actor Dustin Hoffman.
-
E.
Chanelle Peloso
Chanelle Peloso is a Canadian actress known for her roles in television series and films aimed at teen and young adult audiences.
- 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67839e7b48190876ce7133a20c65b |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.