Triple
T9539478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Risto Ryti |
E230110
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object | Kyösti Kallio |
E41097
|
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: Kyösti Kallio | Statement: [Risto Ryti, precededBy, Kyösti Kallio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kyösti Kallio Context triple: [Risto Ryti, precededBy, Kyösti Kallio]
-
A.
Kyösti Kallio
chosen
Kyösti Kallio was a Finnish politician who served as the fourth President of Finland from 1937 to 1940, leading the country through the early stages of World War II.
-
B.
Reijo Kela
Reijo Kela is a Finnish performance and environmental artist known for large-scale, site-specific works that blend sculpture, landscape, and conceptual art.
-
C.
Pertti Paasio
Pertti Paasio was a Finnish Social Democratic politician who served as party leader and held several prominent parliamentary and ministerial roles in Finland.
-
D.
Paavo Haavikko
Paavo Haavikko was a prominent Finnish poet, playwright, and publisher, regarded as one of the most influential figures in 20th-century Finnish literature.
-
E.
Hannu Heikkinen
Hannu Heikkinen is a structural engineer known for his work on the design and construction of Toronto City Hall.
- 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_69ca847b1b3081908f72bc932c17cc41 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98e4df6c8190a4d1160c42daa45f |
completed | April 1, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1e3e92c4c819094cbd2661c425b7c |
completed | April 5, 2026, 4:24 a.m. |
Created at: March 30, 2026, 8:01 p.m.