Triple
T21933287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siskel & Ebert |
E541624
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object | Sneak Previews |
—
|
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: Sneak Previews | Statement: [Siskel & Ebert, precededBy, Sneak Previews]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sneak Previews Context triple: [Siskel & Ebert, precededBy, Sneak Previews]
-
A.
Sneak Previews
chosen
Sneak Previews was an influential American television show that popularized film criticism for a broad audience, co-hosted by Roger Ebert and Gene Siskel.
-
B.
The Preview
The Preview is a 2010 mixtape by hip hop duo Chiddy Bang that helped establish their reputation with its blend of alternative rap and pop-influenced production.
-
C.
Coming Attractions
"Coming Attractions" is an early comedic novel by American author Fannie Flagg, showcasing her trademark Southern charm and humor that she later became widely known for in works like "Fried Green Tomatoes at the Whistle Stop Cafe."
-
D.
Preschau
Preschau is the German name for the city of Prešov, a historic urban center in eastern Slovakia.
-
E.
Preview
Preview is a macOS application used primarily for viewing and editing images and PDF documents.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12400a1248190b3f8f27f2aa4a858 |
completed | April 28, 2026, 9:17 p.m. |
Created at: April 16, 2026, 7:47 p.m.