Triple
T17873992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Escape from Sobibor |
E446903
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Leon Feldhendler |
—
|
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: Leon Feldhendler | Statement: [Escape from Sobibor, mainCharacter, Leon Feldhendler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leon Feldhendler Context triple: [Escape from Sobibor, mainCharacter, Leon Feldhendler]
-
A.
Leon Feldhendler
chosen
Leon Feldhendler was a Polish Jewish resistance leader and Holocaust survivor best known for co-organizing the 1943 prisoner uprising at the Sobibor extermination camp.
-
B.
Len Fichtelberg
Len Fichtelberg was a music industry executive best known as the founder of the influential hip-hop label Cold Chillin' Records.
-
C.
Walter Feldman
Walter Feldman is a Brazilian painter, printmaker, and sculptor known for his contributions to modern and contemporary art in Brazil.
-
D.
Allen Boretz
Allen Boretz was an American playwright and screenwriter best known for his work in mid-20th-century theater and film comedies.
-
E.
Leo Salkin
Leo Salkin was an American animator, writer, and storyboard artist known for his work on mid-20th-century animated films and shorts.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa4959881908774dafb7be99191 |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 10:18 a.m.