Triple
T19879646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ennis Cosby |
E477733
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Erika Cosby |
—
|
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: Erika Cosby | Statement: [Ennis Cosby, sibling, Erika Cosby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erika Cosby Context triple: [Ennis Cosby, sibling, Erika Cosby]
-
A.
Erika Cosby
chosen
Erika Cosby is an American artist and art professor known for her contemporary paintings and as the daughter of comedian Bill Cosby.
-
B.
Camille Cosby
Camille Cosby is an American television producer, philanthropist, and business manager best known for her long marriage to comedian Bill Cosby and her behind-the-scenes influence on his career.
-
C.
Ericka Huggins
Ericka Huggins is an American activist, educator, and former leading member of the Black Panther Party known for her work in prison abolition, social justice, and community-based education.
-
D.
Cynthia Snodgrass
Cynthia Snodgrass is the daughter of Pulitzer Prize–winning American poet W. D. Snodgrass.
-
E.
Larissa Weems
Larissa Weems is a character from the Netflix series "Wednesday," serving as the poised and enigmatic principal of Nevermore Academy.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658dd869c81908aed91ee767f5f3d |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.