Triple
T14378623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curd Jürgens |
E356540
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Eva Bartok |
E398432
|
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: Eva Bartok | Statement: [Curd Jürgens, spouse, Eva Bartok]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eva Bartok Context triple: [Curd Jürgens, spouse, Eva Bartok]
-
A.
Eva Bartok
chosen
Eva Bartok was a Hungarian-born British film actress known for her roles in 1950s and 1960s European and British cinema, including thrillers and adventure films.
-
B.
Éva Gábor
Éva Gábor was a Hungarian-American actress, singer, and businesswoman best known for her role as Lisa Douglas on the television sitcom "Green Acres."
-
C.
Márta Eggerth
Márta Eggerth was a Hungarian-born soprano and film actress renowned for her operetta performances in Europe and Hollywood during the 1930s and 1940s.
-
D.
Margit Vészi
Margit Vészi was a Hungarian journalist and writer, known both for her own literary work and as the wife of celebrated playwright Ferenc Molnár.
-
E.
Lili Darvas
Lili Darvas was a Hungarian-born stage and film actress renowned for her work in European theatre and later on Broadway and American television.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900a67e08190ab1dcf36e6bb3405 |
completed | April 14, 2026, 7:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c5728fc819089ef3c7c34b10101 |
completed | May 8, 2026, 2:37 a.m. |
Created at: April 10, 2026, 1:16 a.m.