Triple
T20990990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stealth (2005 film) |
E517022
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Stephen Rivkin |
—
|
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: Stephen Rivkin | Statement: [Stealth (2005 film), editedBy, Stephen Rivkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stephen Rivkin Context triple: [Stealth (2005 film), editedBy, Stephen Rivkin]
-
A.
Stephen E. Rivkin
chosen
Stephen E. Rivkin is an American film editor best known for his work on major feature films including the "Avatar" series.
-
B.
Allen Rivkin
Allen Rivkin was an American screenwriter active during Hollywood’s studio era, known for his work on numerous mid-20th-century films.
-
C.
Arthur Pearlstein
Arthur Pearlstein is an American lawyer and mediator known for his work in dispute resolution and public service, including leadership roles in federal mediation and conciliation efforts.
-
D.
Lawrence Weingarten
Lawrence Weingarten was an American film producer best known for his work at MGM during Hollywood’s classic studio era, overseeing numerous popular comedies and dramas.
-
E.
David Rosenblum
David Rosenblum is a prominent computer scientist known for his influential research in software engineering and formal methods.
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc1ba3d0819080d9d03817a45026 |
completed | April 21, 2026, 4:24 a.m. |
Created at: April 16, 2026, 1:50 p.m.