Triple
T19389630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Wells |
E485029
|
entity |
| Predicate | screenwriterOfWork |
P25235
|
FINISHED |
| Object | David Berenbaum |
—
|
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: David Berenbaum | Statement: [Susan Wells, screenwriterOfWork, David Berenbaum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Berenbaum Context triple: [Susan Wells, screenwriterOfWork, David Berenbaum]
-
A.
David Berenbaum
chosen
David Berenbaum is an American screenwriter best known for writing the popular Christmas comedy film "Elf."
-
B.
Paul Bernbaum
Paul Bernbaum is an American screenwriter best known for writing the Disney Channel fantasy film "Halloweentown."
-
C.
Charles Bornstein
Charles Bornstein is a film editor best known for his work on genre films such as John Carpenter’s horror movie "The Fog."
-
D.
Michael Berenbaum
Michael Berenbaum is an American scholar, rabbi, and Holocaust historian known for his work on Holocaust education, museum development, and numerous books and films on Jewish history and memory.
-
E.
Michael Berenbaum
Michael Berenbaum is an American film and television editor known for his work on numerous popular comedies and dramas.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b4328448190b6347c41265e820c |
completed | April 20, 2026, 12:25 p.m. |
Created at: April 10, 2026, 1:36 p.m.