Triple
T21718649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virtuality |
E536096
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Joy Bryant |
—
|
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: Joy Bryant | Statement: [Virtuality, castMember, Joy Bryant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joy Bryant Context triple: [Virtuality, castMember, Joy Bryant]
-
A.
Joy Bryant
chosen
Joy Bryant is an American actress and former fashion model best known for her role as Jasmine Trussell on the television series "Parenthood."
-
B.
Joy Behar
Joy Behar is an American comedian, actress, and television host best known as a longtime co-host of the daytime talk show "The View."
-
C.
Audra Phillips
Audra Phillips is a fictional actress and the wife of writer Bill Denbrough in Stephen King’s horror novel "It."
-
D.
Elaine Chappelle
Elaine Chappelle is the wife of comedian Dave Chappelle and the mother of their three children, known for maintaining a private life away from the public spotlight.
-
E.
Shari Headley
Shari Headley is an American actress best known for her role as Lisa McDowell in the classic comedy film "Coming to America."
- 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_69e0c46c6dd88190a595375fa6ebd701 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efd96cc58081908dda09819041b888 |
completed | April 27, 2026, 9:47 p.m. |
Created at: April 16, 2026, 6:47 p.m.