Triple
T20164179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cindy Vortex |
E491786
|
entity |
| Predicate | voiceActor |
P1507
|
FINISHED |
| Object | Carolyn Lawrence |
—
|
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: Carolyn Lawrence | Statement: [Cindy Vortex, voiceActor, Carolyn Lawrence]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carolyn Lawrence Context triple: [Cindy Vortex, voiceActor, Carolyn Lawrence]
-
A.
Carolyn Lawrence
chosen
Carolyn Lawrence is an American voice actress best known for voicing Sandy Cheeks in the SpongeBob SquarePants franchise.
-
B.
Carolyn Surtees
Carolyn Surtees is known as the wife of acclaimed American cinematographer Bruce Surtees.
-
C.
Carolyn Dowling
Carolyn Dowling was the wife of American actor DeForest Kelley, best known for his role as Dr. Leonard "Bones" McCoy in the original Star Trek television series.
-
D.
Carolyn McCormick
Carolyn McCormick is an American actress best known for her recurring role as Dr. Elizabeth Olivet on the television series "Law & Order."
-
E.
Carolyn Leigh
Carolyn Leigh was an American lyricist best known for her witty, sophisticated songs for Broadway and popular music, including classics like "Witchcraft" and "The Best Is Yet to Come."
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6684376408190a68890ab48fa5424 |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.