Triple
T1615041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leo Baeck |
E34697
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Leo Baeck |
E34697
|
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: Leo Baeck | Statement: [Leo Baeck, name, Leo Baeck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leo Baeck Context triple: [Leo Baeck, name, Leo Baeck]
-
A.
Leo Baeck
chosen
Leo Baeck was a prominent German rabbi, theologian, and leader of German Jewry, best known for his religious scholarship and his role representing Jews under Nazi persecution.
-
B.
Fritz Pfeffer
Fritz Pfeffer was a German-Jewish dentist who went into hiding with Anne Frank and others in Amsterdam during the Nazi occupation and was later portrayed as "Albert Dussel" in her diary.
-
C.
Rabbi Joachim Prinz
Rabbi Joachim Prinz was a German-American rabbi and civil rights leader known for his outspoken opposition to Nazism and his prominent speech at the 1963 March on Washington.
-
D.
Otto Dietrich
Otto Dietrich was a high-ranking Nazi official who served as Adolf Hitler’s Press Chief and was later convicted for war crimes at the Nuremberg Ministries Trial.
-
E.
Leo Friedlander
Leo Friedlander was an American sculptor known for his large-scale public monuments and architectural sculpture, particularly in the mid-20th century.
- 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_69a885ffc5ec819091afa325d5f9611c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9098f384c81909ef836ee779466e2 |
completed | March 5, 2026, 4:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad58c6d7e88190b9fc0e34a007a2f5 |
completed | March 8, 2026, 11:08 a.m. |
Created at: March 4, 2026, 7:28 p.m.