Triple
T2232274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silver Streak |
E49195
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object | Gene Wilder |
E238650
|
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: Gene Wilder | Statement: [Silver Streak, starredActor, Gene Wilder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gene Wilder Context triple: [Silver Streak, starredActor, Gene Wilder]
-
A.
Gene Wilder
chosen
Gene Wilder was an American comic actor and writer best known for his roles in films such as Willy Wonka & the Chocolate Factory, Young Frankenstein, and Blazing Saddles.
-
B.
Walter Matthau
Walter Matthau was an American actor renowned for his gruff charm and comedic roles in films such as "The Odd Couple" and "The Bad News Bears."
-
C.
Charles Grodin
Charles Grodin was an American actor, comedian, and writer known for his deadpan delivery in films such as "The Heartbreak Kid," "Midnight Run," and the "Beethoven" series.
-
D.
Charles Matthau
Charles Matthau is an American film and television director and producer, and the son of actor Walter Matthau.
-
E.
Fred Willard
Fred Willard was an American comedic actor and improviser known for his deadpan delivery and scene-stealing roles in mockumentaries like "Best in Show" and numerous television comedies.
- 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc06d26bc8190a85ddb6312d2df08 |
completed | March 7, 2026, 6:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae95fb20b88190b7e959b5d718fe73 |
completed | March 9, 2026, 9:42 a.m. |
Created at: March 4, 2026, 7:47 p.m.