Triple
T3402948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jason Sudeikis |
E71697
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | George Wendt |
E325140
|
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: George Wendt | Statement: [Jason Sudeikis, relative, George Wendt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: George Wendt Context triple: [Jason Sudeikis, relative, George Wendt]
-
A.
George Wendt
chosen
George Wendt is an American actor best known for playing the lovable bar regular Norm Peterson on the classic sitcom "Cheers."
-
B.
John Ratzenberger
John Ratzenberger is an American actor and voice actor best known for his role as Cliff Clavin on "Cheers" and for voicing characters in numerous Pixar animated films.
-
C.
Timothy Newhart
Timothy Newhart is one of the children of American television personality and producer Ginny Newhart and comedian-actor Bob Newhart.
-
D.
Carroll O’Connor
Carroll O’Connor was an American actor best known for his iconic portrayal of Archie Bunker on the groundbreaking television sitcom "All in the Family."
-
E.
Ted Knight
Ted Knight was an American actor and comedian best known for his Emmy-winning role as the pompous newscaster Ted Baxter on the television sitcom "The Mary Tyler Moore 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_69ad85aac4808190a092c9cc8911f584 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb8e78ec8819089417666dc29f412 |
completed | March 8, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b34bd4d02881909c365e054148ae8c |
completed | March 12, 2026, 11:27 p.m. |
Created at: March 8, 2026, 3:14 p.m.