Triple
T19974017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luc Hoffmann |
E493639
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Maja Hoffmann |
—
|
NE NERFINISHED |
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: Maja Hoffmann | Statement: [Luc Hoffmann, hasChild, Maja Hoffmann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maja Hoffmann Context triple: [Luc Hoffmann, hasChild, Maja Hoffmann]
-
A.
Maja Hoffmann
chosen
Maja Hoffmann is a Swiss art patron, philanthropist, and founder of the LUMA Foundation, known for her influential support of contemporary art and cultural projects.
-
B.
Therese Hoffmann
Therese Hoffmann was the mother of Henriette von Schirach, a German woman known for her close association with the Nazi leadership through her marriage to Baldur von Schirach.
-
C.
Christiane Knef
Christiane Knef is the daughter of renowned German actress and singer Hildegard Knef.
-
D.
Eva Mattes
Eva Mattes is a German actress known for her extensive work in film, television, and theater, including collaborations with directors like Rainer Werner Fassbinder and Werner Herzog.
-
E.
Sabine Hoffman
Sabine Hoffman is a film editor known for her work on independent and art-house films, including the acclaimed drama "Personal Velocity."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65bcb72048190aedb4f085ace0493 |
completed | April 20, 2026, 5 p.m. |
Created at: April 11, 2026, 3:23 p.m.