Triple
T12156987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate Bosworth |
E289598
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Michael Polish |
E774159
|
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: Michael Polish | Statement: [Kate Bosworth, spouse, Michael Polish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Polish Context triple: [Kate Bosworth, spouse, Michael Polish]
-
A.
Michael Polish
chosen
Michael Polish is an American film director, screenwriter, and actor best known for his work on independent films such as "Twin Falls Idaho" and "Northfork."
-
B.
Tomasz Kulik
Tomasz Kulik is a person notable enough to be recognized as a distinct namesake of the surname Kulik.
-
C.
Piotr Lipiński
Piotr Lipiński is a Polish writer and journalist known for his historical reportage and works on 20th-century Polish history.
-
D.
Peter Kaczorowski
Peter Kaczorowski is an American theatrical lighting designer renowned for his work on major Broadway productions.
-
E.
Jan Nowak
Jan Nowak was the wartime pseudonym of Jan Nowak-Jeziorański, a renowned Polish resistance courier, journalist, and later influential émigré activist and director of the Polish section of Radio Free Europe.
- 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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915c1673c8190830cd15525d16869 |
completed | April 10, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f69c8d408190abbc900deb534045 |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:50 p.m.