Triple
T15750212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leopold Page |
E381824
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Leopold Pfefferberg |
E383745
|
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: Leopold Pfefferberg | Statement: [Leopold Page, birthName, Leopold Pfefferberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leopold Pfefferberg Context triple: [Leopold Page, birthName, Leopold Pfefferberg]
-
A.
Poldek Pfefferberg
chosen
Poldek Pfefferberg was a Polish Jewish Holocaust survivor and businessman who played a crucial role in publicizing Oskar Schindler’s story, inspiring the book and film "Schindler’s List."
-
B.
Armond Lebowitz
Armond Lebowitz is a film editor known for his work on genre movies, including the horror film "A Return to Salem's Lot."
-
C.
George Nachman
George Nachman is a software engineer best known as the creator and maintainer of the popular macOS terminal emulator iTerm2.
-
D.
Myron Futterman
Myron Futterman was an American businessman best known for being the first husband of actress Jane Wyman.
-
E.
Joel Teitelbaum
Joel Teitelbaum was a prominent Hasidic rabbi and founding Satmar Rebbe, known for leading and shaping the Satmar Hasidic community.
- 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_69d86d9e6b44819085d1f6a969ecb74c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0502fd3608190b42e647b9c2b41a1 |
completed | April 16, 2026, 2:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff998397688190a77b6a7c5b542f7e |
completed | May 9, 2026, 8:30 p.m. |
Created at: April 10, 2026, 4:47 a.m.