Triple
T15710681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Berg |
E380828
|
entity |
| Predicate | romanticPartner |
P9994
|
FINISHED |
| Object | Hanna Schmitz |
E380829
|
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: Hanna Schmitz | Statement: [Michael Berg, romanticPartner, Hanna Schmitz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hanna Schmitz Context triple: [Michael Berg, romanticPartner, Hanna Schmitz]
-
A.
Hanna Schmitz
chosen
Hanna Schmitz is a central, morally complex character in Bernhard Schlink’s novel *The Reader*, known for her secret illiteracy and her involvement in Nazi war crimes.
-
B.
Angelica Schmitz
Angelica Schmitz was the wife of Ukrainian-American avant-garde sculptor Alexander Archipenko, associated with his personal and artistic life.
-
C.
Emma Schlamme
Emma Schlamme is the daughter of American actress and filmmaker Christine Lahti and television director Thomas Schlamme.
-
D.
Anja Tschimiakin
Anja Tschimiakin was the first wife of Russian abstract art pioneer Wassily Kandinsky.
-
E.
Juliane Köhler
Juliane Köhler is a German actress known for her acclaimed performances in film, television, and theater, including award-winning roles in internationally recognized German cinema.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f8f5d6081908243fa59b46b7c76 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff997fe6f48190813bde2bfc11c253 |
completed | May 9, 2026, 8:30 p.m. |
Created at: April 10, 2026, 4:45 a.m.