Triple
T20645330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slice |
E507340
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Zazie Beetz |
—
|
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: Zazie Beetz | Statement: [Slice, starring, Zazie Beetz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zazie Beetz Context triple: [Slice, starring, Zazie Beetz]
-
A.
Zazie Beetz
chosen
Zazie Beetz is a German-American actress known for her roles in the TV series "Atlanta" and films such as "Deadpool 2" and "Joker."
-
B.
Yaya DaCosta
Yaya DaCosta is an American actress and model known for her work in film, television, and fashion, including roles in "America's Next Top Model," "The Butler," and "Chicago Med."
-
C.
Awkwafina
Awkwafina is an American actress, comedian, and rapper known for her breakout roles in films like "Crazy Rich Asians" and "The Farewell," as well as her distinctive comedic persona.
-
D.
Leslie Jones
Leslie Jones is an American comedian and actress known for her work on "Saturday Night Live" and roles in films such as the 2016 "Ghostbusters" reboot.
-
E.
Leslie Jones
Leslie Jones is an American film editor known for her work on major Hollywood productions, including the feature film "Starsky & Hutch."
- 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_69e0b4be702c8190a3d2410a881d310a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af1dd79481909de985d03ab861c2 |
completed | April 20, 2026, 10:56 p.m. |
Created at: April 16, 2026, 11:43 a.m.