Triple
T19452421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jenji Kohan |
E486644
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mad About You |
—
|
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: Mad About You | Statement: [Jenji Kohan, notableWork, Mad About You]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mad About You Context triple: [Jenji Kohan, notableWork, Mad About You]
-
A.
Mad About You
chosen
Mad About You is a popular 1990s American sitcom that follows the everyday lives and relationship of a married couple in New York City, known for its witty dialogue and strong lead performances.
-
B.
Mad About You
"Mad About You" is a 1986 pop song by American singer Belinda Carlisle, released as one of her early solo hits after leaving the Go-Go's.
-
C.
Nobody but You
"Nobody but You" is a country duet by Blake Shelton and Gwen Stefani that became a popular romantic hit upon its release in 2020.
-
D.
Mad Love
"Mad Love" is a 1935 psychological horror film starring Peter Lorre (credited as László Löwenstein), known for its macabre tale of obsession and surgical mutilation.
-
E.
Mad Love
"Mad Love" is a popular dancehall-pop song by Jamaican artist Sean Paul, known for its catchy hook and club-friendly production.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63392aab08190aab09b7c356e5b10 |
completed | April 20, 2026, 2:09 p.m. |
Created at: April 10, 2026, 1:38 p.m.