Triple
T19532805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boss (TV series) |
E488695
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Sanaa Lathan |
—
|
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: Sanaa Lathan | Statement: [Boss (TV series), starring, Sanaa Lathan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sanaa Lathan Context triple: [Boss (TV series), starring, Sanaa Lathan]
-
A.
Sanaa Lathan
chosen
Sanaa Lathan is an American actress known for her work in film, television, and voice acting, including prominent roles in movies like "Love & Basketball" and "Brown Sugar."
-
B.
Jordana Brewster
Jordana Brewster is a Panamanian-American actress best known for her role as Mia Toretto in the Fast & Furious film franchise.
-
C.
Angelica Bullock
Angelica Bullock is the eccentric, status-conscious matriarch of the wealthy Bullock family in the classic screwball comedy film "My Man Godfrey."
-
D.
Deva Cassel
Deva Cassel is an Italian model and emerging actress, known as the daughter of Monica Bellucci and Vincent Cassel.
-
E.
T'Nia Miller
T'Nia Miller is a British actress known for her powerful performances in television dramas such as "The Haunting of Bly Manor," "Years and Years," and various other genre and prestige series.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6364091f4819088b27d0ffdf6010d |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.