Triple
T21490306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Jon |
E530218
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Scarlett Johansson |
—
|
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: Scarlett Johansson | Statement: [Don Jon, castMember, Scarlett Johansson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scarlett Johansson Context triple: [Don Jon, castMember, Scarlett Johansson]
-
A.
Scarlett Johansson
chosen
Scarlett Johansson is an American actress known for her versatile film roles, including major parts in the Marvel Cinematic Universe and acclaimed performances in both independent and blockbuster movies.
-
B.
Brie Larson
Brie Larson is an Academy Award–winning American actress known for her versatile performances in films such as Room, Captain Marvel, and Kong: Skull Island.
-
C.
Jess Wasikowska
Jess Wasikowska is a sibling of Australian actress Mia Wasikowska, known for her role in films such as "Alice in Wonderland."
-
D.
Marzen Wasikowska
Marzen Wasikowska is the mother of Australian actress Mia Wasikowska.
-
E.
Jennifer Kilmer
Jennifer Kilmer is the wife of U.S. Congressman Derek Kilmer and is known publicly in connection with his political and community life.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea3aee648190ba845f0c7d8110dd |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:22 p.m.