Triple
T2848626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnold Schoenberg |
E63039
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mathilde Zemlinsky |
E73599
|
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: Mathilde Zemlinsky | Statement: [Arnold Schoenberg, spouse, Mathilde Zemlinsky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mathilde Zemlinsky Context triple: [Arnold Schoenberg, spouse, Mathilde Zemlinsky]
-
A.
Rosa Stradner
Rosa Stradner was an Austrian-born actress who appeared in European and Hollywood films in the 1930s and 1940s.
-
B.
Marie Schumann
Marie Schumann was the eldest daughter of composers Robert and Clara Schumann, known primarily for preserving and managing her parents’ musical legacy.
-
C.
Alma Mahler
chosen
Alma Mahler was an Austrian composer, socialite, and muse at the center of early 20th-century Viennese artistic circles, known for her relationships with several prominent artists and intellectuals.
-
D.
Hedwig Hensel
Hedwig Hensel was the wife of Rudolf Höss, the commandant of the Auschwitz concentration camp during World War II.
-
E.
Dora Maurer
Dora Maurer is a Hungarian conceptual artist and filmmaker known for her experimental works exploring perception, movement, and systems-based processes.
- 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_69ab4c407c408190857d25e027155ce9 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf403698819084fb4ace5839aa05 |
completed | March 7, 2026, 8:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afe8df46c881909a5f0d1d0eef9a42 |
completed | March 10, 2026, 9:48 a.m. |
Created at: March 6, 2026, 10:02 p.m.