Triple
T2393288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gregory Peck |
E48990
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Greta Kukkonen |
E48990
|
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: Greta Kukkonen | Statement: [Gregory Peck, spouse, Greta Kukkonen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greta Kukkonen Context triple: [Gregory Peck, spouse, Greta Kukkonen]
-
A.
Greta Kukkonen
chosen
Greta Kukkonen was a Finnish-born American humanitarian and the first wife of actor Gregory Peck, known for her charitable work and support of Finnish relief efforts.
-
B.
Märta Tikkanen
Märta Tikkanen is a Finnish-Swedish author and feminist known for her influential novels and poetry exploring gender roles, marriage, and women's liberation.
-
C.
Ellen Svinhufvud
Ellen Svinhufvud was the wife of Finnish statesman and third President of Finland Pehr Evind Svinhufvud and served as First Lady of Finland during his presidency.
-
D.
Aino Kallio
Aino Kallio was the wife of renowned Finnish poet and national romantic figure Eino Leino.
-
E.
Sylvi Kekkonen
Sylvi Kekkonen was a Finnish writer and the long-serving First Lady of Finland during the presidency of her husband, Urho Kekkonen.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc876d48881909e4d6f5ebe430012 |
completed | March 7, 2026, 6:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aebf3a3a2c8190a29b8ce47e40c3f8 |
completed | March 9, 2026, 12:38 p.m. |
Created at: March 4, 2026, 7:57 p.m.