Triple
T13486469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saving Silverman |
E318516
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jason Biggs |
E137345
|
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: Jason Biggs | Statement: [Saving Silverman, starring, Jason Biggs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jason Biggs Context triple: [Saving Silverman, starring, Jason Biggs]
-
A.
Jason Biggs
chosen
Jason Biggs is an American actor best known for his comedic role as Jim Levenstein in the "American Pie" film series.
-
B.
Josh Peck
Josh Peck is an American actor and comedian best known for his role on the Nickelodeon series "Drake & Josh" and his subsequent work in film, television, and online media.
-
C.
Josh Stewart
Josh Stewart is an American actor known for his roles in films like "The Collector" series and "The Dark Knight Rises" as well as television shows such as "Criminal Minds."
-
D.
Chris O'Donnell
Chris O'Donnell is an American actor best known for his film roles in the 1990s and for starring as Special Agent G. Callen on the television series NCIS: Los Angeles.
-
E.
Skeet Ulrich
Skeet Ulrich is an American actor best known for his roles in films like "Scream" and "The Craft" and the television series "Jericho."
- 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_69d806b6bfec819089222715b2e86c8e |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf3a15b48190b63fb59e926a97ae |
completed | April 12, 2026, 2:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f74638e2088190a126791f60b541c7 |
completed | May 3, 2026, 12:57 p.m. |
Created at: April 9, 2026, 9:42 p.m.