Triple
T20140328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miss Virginia |
E491145
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Vanessa Williams |
—
|
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: Vanessa Williams | Statement: [Miss Virginia, castMember, Vanessa Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vanessa Williams Context triple: [Miss Virginia, castMember, Vanessa Williams]
-
A.
Vanessa Williams
chosen
Vanessa Williams is an American singer, actress, and former Miss America known for her successful music career and prominent roles in film, television, and theater.
-
B.
Petra Williams
Petra Williams is a fictional character appearing in the narrative of "Inferno."
-
C.
Elizabeth Way
Elizabeth Way is a major road in Cambridge, England, forming part of the city’s inner ring road and providing a key route across the River Cam.
-
D.
Sherie Rene Scott
Sherie Rene Scott is a Tony-nominated American actress and singer known for her work in numerous Broadway productions and original musical roles.
-
E.
Malinda Williams
Malinda Williams is an American actress known for her roles in film and television, particularly in projects like the series "Soul Food" and various romantic comedies and dramas.
- 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66798d59c81908ebcd6644b1b3744 |
completed | April 20, 2026, 5:51 p.m. |
Created at: April 11, 2026, 11:32 p.m.