Triple
T23486747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vic Tayback |
E570553
|
entity |
| Predicate | characterRole |
P268
|
FINISHED |
| Object | Mel Sharples |
—
|
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: Mel Sharples | Statement: [Vic Tayback, characterRole, Mel Sharples]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mel Sharples Context triple: [Vic Tayback, characterRole, Mel Sharples]
-
A.
Mel Sharples
chosen
Mel Sharples is a gruff but good-hearted diner owner and cook from the sitcom "Alice," known for his no-nonsense attitude and catchphrase, "Stow it!"
-
B.
Merritt Andrews
Merritt Andrews is a fictional character played by actress Yvette Mimieux, best known from her work in mid-20th-century American film and television.
-
C.
Warren Sharples
Warren Sharples is a musician known for being a member of the new wave band Tom Tom Club.
-
D.
Peleg Sangerville
Peleg Sangerville was an individual after whom the town of Sangerville, Maine, was named, indicating his historical significance to the area.
-
E.
Hal Sharp
Hal Sharp is a comic book writer and creator best known for his work on the DC Comics superhero Mr. Terrific.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a754825481909b005ca5654c3159 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:04 p.m.