Triple
T6788786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Funny You Should Ask |
E155879
|
entity |
| Predicate | host |
P2592
|
FINISHED |
| Object | Jon Kelley |
E636557
|
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: Jon Kelley | Statement: [Funny You Should Ask, host, Jon Kelley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jon Kelley Context triple: [Funny You Should Ask, host, Jon Kelley]
-
A.
Jon Kelley
chosen
Jon Kelley is an American television personality and sportscaster best known for hosting game and entertainment shows, including the comedy game show "Funny You Should Ask."
-
B.
Jack Kelley
Jack Kelley was an American ice hockey coach best known for leading the New England Whalers to early success in the World Hockey Association.
-
C.
Josh Kelley
Josh Kelley is an American singer-songwriter known for his blend of pop, rock, and country influences and for hits like "Amazing" and "Only You."
-
D.
Andrew Kelley
Andrew Kelley is a software engineer best known as the creator and lead developer of the Zig programming language.
-
E.
Kelley Paul
Kelley Paul is an American political consultant, author, and public speaker best known as the wife and close political adviser of U.S. Senator Rand Paul.
- 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_69c6881770fc8190972b2906390380f5 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2aa2e0c8190b994261826ae001d |
completed | March 27, 2026, 6:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7881214488190914a3ee08fce359e |
completed | March 28, 2026, 7:49 a.m. |
Created at: March 27, 2026, 2:14 p.m.