Triple
T13003755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mikael Blomkvist |
E322233
|
entity |
| Predicate | romanticallyInvolvedWith |
P9994
|
FINISHED |
| Object | Erika Berger |
E1055932
|
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: Erika Berger | Statement: [Mikael Blomkvist, romanticallyInvolvedWith, Erika Berger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erika Berger Context triple: [Mikael Blomkvist, romanticallyInvolvedWith, Erika Berger]
-
A.
Erika Berger
chosen
Erika Berger is a prominent magazine editor and Mikael Blomkvist’s longtime professional and romantic partner in Stieg Larsson’s Millennium series.
-
B.
Erika Peters
Erika Peters is a German-born actress known for her film and television work in the 1950s and 1960s.
-
C.
Lisa Eilbacher
Lisa Eilbacher is an American actress best known for her roles in 1980s films and television series, including prominent appearances in action and drama movies.
-
D.
Erika Eleniak
Erika Eleniak is an American actress and former Playboy Playmate best known for her roles in the TV series "Baywatch" and films such as "Under Siege."
-
E.
Stefanie Ehrlich
Stefanie Ehrlich is known as a child of the prominent American biologist and author Paul Ehrlich.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e9a2a448190968833354280e474 |
completed | April 10, 2026, 10:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d3188f88190aafbb1cf97317dc8 |
completed | May 3, 2026, 7:08 p.m. |
Created at: April 9, 2026, 8:47 p.m.