Triple
T8375985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh John Mungo Grant |
E197575
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Anna Elisabet Eberstein |
E250374
|
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: Anna Elisabet Eberstein | Statement: [Hugh John Mungo Grant, spouse, Anna Elisabet Eberstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anna Elisabet Eberstein Context triple: [Hugh John Mungo Grant, spouse, Anna Elisabet Eberstein]
-
A.
Anna Eberstein
chosen
Anna Eberstein is a Swedish television producer and retail executive best known as the wife of British actor Hugh Grant.
-
B.
Elisabeth Helene von Vieregg
Elisabeth Helene von Vieregg was a German noblewoman best known as the morganatic wife of King Frederick IV of Denmark–Norway.
-
C.
Adelheid Zunz
Adelheid Zunz was the wife of the prominent German Jewish scholar and historian Leopold Zunz, a key figure in the development of modern Jewish studies.
-
D.
Luise von Benda
Luise von Benda was the wife of German World War II General Alfred Jodl, a senior military leader in Nazi Germany.
-
E.
Astrid Eckert
Astrid Eckert is a historian and academic known for her work on modern German history, memory culture, and the legacy of the Cold War.
- 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_69ca82f64c188190af4e1608036b865d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80bf6b8081909b98762b1f900bef |
completed | March 31, 2026, 8:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea813e384819090a8a7dc05e41ab2 |
completed | April 2, 2026, 5:32 p.m. |
Created at: March 30, 2026, 6:01 p.m.