Triple
T13351218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Velma Dinkley |
E318071
|
entity |
| Predicate | voiceActedBy |
P39669
|
FINISHED |
| Object | Mindy Cohn |
E230787
|
NE FINISHED |
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: Mindy Cohn | Statement: [Velma Dinkley, voiceActedBy, Mindy Cohn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mindy Cohn Context triple: [Velma Dinkley, voiceActedBy, Mindy Cohn]
-
A.
Mindy Cohn
chosen
Mindy Cohn is an American actress best known for playing Natalie Green on the classic television sitcom "The Facts of Life."
-
B.
Mindi Abair
Mindi Abair is an American saxophonist, vocalist, and songwriter known for her contemporary jazz and pop-influenced performances and recordings.
-
C.
Jean Grae
Jean Grae is an American underground hip-hop MC known for her intricate lyricism, sharp wordplay, and influential role in New York’s indie rap scene.
-
D.
Mary Lou Jepsen
Mary Lou Jepsen is an American engineer, inventor, and entrepreneur known for her pioneering work in display technology and for co-founding the low-cost computing initiative One Laptop per Child.
-
E.
Debra Freer
Debra Freer is a writer and editor known for her work on the publication of Margaret Mitchell’s early novella "Lost Laysen," for which she contributed the preface.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8c2f1c819094f0970f35f18afa |
completed | April 11, 2026, 1:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f71f47fd7c8190b8d98a181acd7710 |
completed | May 3, 2026, 10:11 a.m. |
Created at: April 9, 2026, 9:31 p.m.