Triple
T23477321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filthy Rich |
E570297
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Delta Burke |
—
|
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: Delta Burke | Statement: [Filthy Rich, hasCastMember, Delta Burke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delta Burke Context triple: [Filthy Rich, hasCastMember, Delta Burke]
-
A.
Delta Burke
chosen
Delta Burke is an American actress and producer best known for her Emmy-nominated role as Suzanne Sugarbaker on the sitcom "Designing Women."
-
B.
Tamdan McCrory
Tamdan McCrory is an American mixed martial artist known for competing in the UFC’s welterweight and middleweight divisions.
-
C.
Tiffany Burress
Tiffany Burress is best known as the wife of former NFL wide receiver Plaxico Burress.
-
D.
Angelica McDaniel
Angelica McDaniel is a television executive and producer best known for her leadership roles in daytime programming and development at major U.S. networks.
-
E.
Kelleigh Bannen
Kelleigh Bannen is an American country music singer-songwriter known for her work in Nashville and releases such as her album "Favorite Colors."
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74dbea8819085ca84391039e7f7 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:01 p.m.