Triple
T18295195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mari Leppänen |
E438212
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Mari Leppänen |
—
|
NE NERFINISHED |
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: Mari Leppänen | Statement: [Mari Leppänen, name, Mari Leppänen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mari Leppänen Context triple: [Mari Leppänen, name, Mari Leppänen]
-
A.
Mari Leppänen
chosen
Mari Leppänen is a Finnish Lutheran prelate who serves as a leading bishop in the Evangelical Lutheran Church of Finland.
-
B.
Mari Kiviniemi
Mari Kiviniemi is a Finnish politician who served as Prime Minister of Finland and leader of the Centre Party in the early 2010s.
-
C.
Kari Jalonen
Kari Jalonen is a Finnish former professional ice hockey player and highly respected coach known for leading top European clubs and national teams.
-
D.
Kirsti Paakkanen
Kirsti Paakkanen was a prominent Finnish businesswoman best known for revitalizing and leading the iconic design company Marimekko.
-
E.
Kari Väänänen
Kari Väänänen is a Finnish actor and director known for his work in both Finnish cinema and international films, including collaborations with acclaimed directors like Aki Kaurismäki.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5017783748190905ce4eeadd25841 |
completed | April 19, 2026, 4:23 p.m. |
Created at: April 10, 2026, 10:35 a.m.