Triple
T10248668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stefan Zweig |
E240283
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Lotte Altmann |
E785723
|
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: Lotte Altmann | Statement: [Stefan Zweig, spouse, Lotte Altmann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lotte Altmann Context triple: [Stefan Zweig, spouse, Lotte Altmann]
-
A.
Elsie Altmann
chosen
Elsie Altmann was an Austrian dancer and actress of the early 20th century, known both for her stage career in Vienna and for her marriage to modernist architect Adolf Loos.
-
B.
Ilse Löwenthal
Ilse Löwenthal was a member of the Löwenthal family, known primarily through her relationship to Elsa Löwenthal, Albert Einstein’s second wife.
-
C.
Lilian Kaufmann
Lilian Kaufmann was a member of the prominent Kaufmann family of Pittsburgh, known as the original owners and patrons of Frank Lloyd Wright’s iconic Fallingwater house.
-
D.
Elsa Löwenthal
Elsa Löwenthal, better known as Elsa Einstein, was the second wife and cousin of physicist Albert Einstein and often managed his personal and social affairs.
-
E.
Edith Hahn
Edith Hahn was the wife of German chemist and Nobel laureate Otto Hahn.
- 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d23b620c8190b8a72d0eb0d16b93 |
completed | April 7, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f7ade8448190830d950b7cee0c34 |
completed | April 9, 2026, 12:49 a.m. |
Created at: April 6, 2026, 11:27 a.m.