Triple
T10811212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Curtiz |
E255102
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Ilona Kovács |
E255102
|
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: Ilona Kovács | Statement: [Michael Curtiz, spouse, Ilona Kovács]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ilona Kovács Context triple: [Michael Curtiz, spouse, Ilona Kovács]
-
A.
Ilona Kovács
chosen
Ilona Kovács was the wife of renowned Hungarian-American film director Michael Curtiz.
-
B.
Ilona Komocsin
Ilona Komocsin was the wife and muse of Hungarian architect and sculptor Jenő Bory, for whom he built the romantic Bory Castle as a monument to their love.
-
C.
Katalin Kovács
Katalin Kovács is a Hungarian sprint canoer and one of the sport’s most decorated athletes, with multiple Olympic and World Championship titles.
-
D.
Katalin Ladik
Katalin Ladik is a Serbian-Hungarian poet, performance artist, and actress known for her experimental sound poetry and avant-garde multimedia work.
-
E.
Márta Károlyi
Márta Károlyi is a Romanian-American gymnastics coach renowned for co-developing the dominant Romanian and later U.S. women's gymnastics programs alongside her husband, Béla Károlyi.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733b7bfac8190b6ae34144376d6ad |
completed | April 9, 2026, 5:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dff7c0907c8190b092bb6754fe4e52 |
completed | April 15, 2026, 8:40 p.m. |
Created at: April 8, 2026, 9:18 p.m.