Triple
T16343321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John William Carson |
E396861
|
entity |
| Predicate | influenced |
P9
|
FINISHED |
| Object | Jay Leno |
E13481
|
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: Jay Leno | Statement: [John William Carson, influenced, Jay Leno]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jay Leno Context triple: [John William Carson, influenced, Jay Leno]
-
A.
Jay Leno
chosen
Jay Leno is an American comedian and longtime host of NBC’s “The Tonight Show,” known for his observational stand-up and prominent role in late-night television.
-
B.
Mark Leno
Mark Leno is an American Democratic politician and former California state legislator known for representing San Francisco in both the State Assembly and State Senate.
-
C.
Leno
Leno is a river in northern Italy that serves as a tributary of the Brenta River.
-
D.
John Carson
John Carson is a fictional character appearing in the film "The Miracle Woman."
-
E.
Ed McMahon
Ed McMahon was an American television personality and announcer best known as Johnny Carson’s longtime sidekick on “The Tonight Show.”
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2da0b88d081908a99cafa8e0ae5db |
completed | April 18, 2026, 1:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002db00b4081909573afc66366a91c |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:07 a.m.