Triple
T6800540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Der große Bellheim |
E156173
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Mario Adorf |
E456987
|
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: Mario Adorf | Statement: [Der große Bellheim, leadActor, Mario Adorf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mario Adorf Context triple: [Der große Bellheim, leadActor, Mario Adorf]
-
A.
Mario Adorf
chosen
Mario Adorf is a renowned German-Swiss actor celebrated for his prolific film and television career across European cinema since the mid-20th century.
-
B.
Victor Heerman
Victor Heerman was a British-born American screenwriter and film director best known for co-writing the Academy Award–winning adaptation of "Little Women" (1933).
-
C.
Peter Facinelli
Peter Facinelli is an American actor best known for playing Dr. Carlisle Cullen in the Twilight film series.
-
D.
Dieter Fox
Dieter Fox is a prominent computer scientist and roboticist known for his contributions to probabilistic robotics, perception, and machine learning in autonomous systems.
-
E.
Udo Kier
Udo Kier is a German actor known for his distinctive, often eccentric performances in European art-house films and cult horror movies, as well as numerous international productions.
- 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_69c6881844448190a65822d9b39d7f88 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2e457408190a0ad9b0c48d8147c |
completed | March 27, 2026, 6:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c72f9926ec8190bff8d01e3ab0d0da |
completed | March 28, 2026, 1:32 a.m. |
Created at: March 27, 2026, 2:15 p.m.