Triple
T17399502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dharma & Greg |
E423049
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Dottie Zicklin |
—
|
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: Dottie Zicklin | Statement: [Dharma & Greg, creator, Dottie Zicklin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dottie Zicklin Context triple: [Dharma & Greg, creator, Dottie Zicklin]
-
A.
Dottie Zicklin
chosen
Dottie Zicklin is an American television writer and producer known for her work on sitcoms such as "Dharma & Greg" and "Younger."
-
B.
Judy Zankel
Judy Zankel was a philanthropist and arts patron whose support and legacy are honored through the naming of Zankel Hall at Carnegie Hall.
-
C.
Judy Marks
Judy Marks is an American business executive best known as the president and CEO of Otis Worldwide Corporation, a leading elevator and escalator company.
-
D.
Carole Lintzenich
Carole Lintzenich is best known as the wife of legendary American sportscaster Jack Buck.
-
E.
Marla Frumkin
Marla Frumkin is an American voice actress best known for portraying Velma Dinkley in the Scooby-Doo animated franchise.
- 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_69d889d710288190bf0f4762801fefae |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43ac0596481908c400916d5c1b971 |
completed | April 19, 2026, 2:15 a.m. |
Created at: April 10, 2026, 5:45 a.m.