Triple
T18234190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Burglar |
E436625
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Paul Wendkos |
—
|
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: Paul Wendkos | Statement: [The Burglar, director, Paul Wendkos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Wendkos Context triple: [The Burglar, director, Paul Wendkos]
-
A.
Paul Wendkos
chosen
Paul Wendkos was an American film and television director known for his work on genre films and numerous TV movies from the 1950s through the 1990s.
-
B.
Paul Rudish
Paul Rudish is an American animator, writer, and director known for his distinctive, retro-inspired style on series like Dexter’s Laboratory, Samurai Jack, and the 2013 Mickey Mouse shorts.
-
C.
Eric Pleskow
Eric Pleskow was an Austrian-born American film executive and producer best known for leading major studios and co-founding the influential independent film company Orion Pictures.
-
D.
Paul Koslo
Paul Koslo was a German-Canadian character actor known for his supporting roles in 1970s and 1980s action and science fiction films.
-
E.
Ken Lemberger
Ken Lemberger is a film producer known for his work on the 2006 adaptation of "All the King's Men."
- 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_69d8b9103a8081908bbb0836fef10efd |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f4b512a88190aa493b0793ab28b3 |
completed | April 19, 2026, 3:28 p.m. |
Created at: April 10, 2026, 10:33 a.m.