Triple
T22663919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zahn |
E559732
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | Steve Zahn |
—
|
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: Steve Zahn | Statement: [Zahn, usedBy, Steve Zahn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steve Zahn Context triple: [Zahn, usedBy, Steve Zahn]
-
A.
Steve Zahn
chosen
Steve Zahn is an American actor known for his comedic and character roles in films such as "That Thing You Do!", "Saving Silverman," and "Sahara," as well as in television and independent cinema.
-
B.
Adam Brody
Adam Brody is an American actor best known for his role as Seth Cohen on the television series "The O.C." and for appearances in various film and television projects.
-
C.
Chris Penn
Chris Penn was an American character actor known for his roles in films such as "Reservoir Dogs," "Footloose," and "True Romance."
-
D.
David Arquette
David Arquette is an American actor, filmmaker, and former professional wrestler best known for his role as Dewey Riley in the "Scream" horror film franchise.
-
E.
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.
- 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f176617ed8819095a58a2c9f1e3918 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 3:08 p.m.