Triple
T14397650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diner |
E356990
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | Peter Sova |
E259291
|
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: Peter Sova | Statement: [Diner, cinematographyBy, Peter Sova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Sova Context triple: [Diner, cinematographyBy, Peter Sova]
-
A.
Peter Sova
chosen
Peter Sova was a Czech-American cinematographer known for his stylish visual work on films such as "Lucky Number Slevin" and collaborations with directors like Barry Levinson.
-
B.
Martin Kove
Martin Kove is an American actor best known for his role as the ruthless sensei John Kreese in the Karate Kid film series and its sequel series Cobra Kai.
-
C.
John Blutarsky
John Blutarsky is a boisterous, hard-partying fraternity member and iconic comedic character from the film "National Lampoon's Animal House," famously portrayed by John Belushi.
-
D.
Michael Socha
Michael Socha is an English actor known for his roles in television dramas and fantasy series, including prominent parts in shows like "Being Human" and "Once Upon a Time in Wonderland."
-
E.
Andrew J. Novobilski
Andrew J. Novobilski is a computer scientist and author known for co-writing influential work on the Objective-C programming language alongside Brad Cox.
- 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_69d827927c988190ad98bb0360981783 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de90826f908190b3969af9b7cf922f |
completed | April 14, 2026, 7:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bc424f88190ab3a1c1aec61cb40 |
completed | May 8, 2026, 3:43 a.m. |
Created at: April 10, 2026, 1:17 a.m.