Triple
T21594719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salome, Where She Danced |
E532867
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Kurt Kreuger |
—
|
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: Kurt Kreuger | Statement: [Salome, Where She Danced, starring, Kurt Kreuger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kurt Kreuger Context triple: [Salome, Where She Danced, starring, Kurt Kreuger]
-
A.
Kurt Kreuger
chosen
Kurt Kreuger was a Swiss-born American actor known for frequently portraying German officers and villains in Hollywood films of the 1940s and 1950s.
-
B.
Karl Krueger
Karl Krueger was an American conductor known for his work with major orchestras and for making early high-fidelity orchestral recordings.
-
C.
Kramer Morgenthau
Kramer Morgenthau is an American cinematographer known for his work on major films and television series, including entries in the Rocky/Creed franchise and various high-profile dramas.
-
D.
Kurt Katch
Kurt Katch was a character actor known for his roles in Hollywood films of the 1930s and 1940s, often portraying sinister or foreign villains.
-
E.
Ralph Dumke
Ralph Dumke was an American character actor known for his supporting roles in mid-20th-century films and television.
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eefae07e388190baf1d67852c7e5db |
completed | April 27, 2026, 5:57 a.m. |
Created at: April 16, 2026, 6:32 p.m.