Triple
T21592178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koskinen |
E532807
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Seppo Koskinen
Seppo Koskinen is a Finnish legal scholar and professor known for his work in labor law and social law.
|
E1502343
|
NE FINISHED |
How this triple was built (4 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: Seppo Koskinen | Statement: [Koskinen, hasNotableBearer, Seppo Koskinen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seppo Koskinen Context triple: [Koskinen, hasNotableBearer, Seppo Koskinen]
-
A.
Reijo Kiilunen
Reijo Kiilunen is a Finnish music producer and entrepreneur best known as the founder of the classical and contemporary music label Ondine Records.
-
B.
Kalle Koskinen
Kalle Koskinen is a Finnish former professional ice hockey defenceman who played in the SM-liiga, notably for JYP Jyväskylä.
-
C.
Seppo Harjanne
Seppo Harjanne is a Finnish rally co-driver best known for partnering with top drivers such as Timo Salonen during the World Rally Championship era.
-
D.
Hannu Heikkinen
Hannu Heikkinen is a structural engineer known for his work on the design and construction of Toronto City Hall.
-
E.
Heikki Savolainen
Heikki Savolainen was a Finnish artistic gymnast and multiple Olympic medalist who became one of Finland’s most successful early 20th-century gymnasts.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Seppo Koskinen Triple: [Koskinen, hasNotableBearer, Seppo Koskinen]
Generated description
Seppo Koskinen is a Finnish legal scholar and professor known for his work in labor law and social law.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Seppo Koskinen Target entity description: Seppo Koskinen is a Finnish legal scholar and professor known for his work in labor law and social law.
-
A.
Reijo Kiilunen
Reijo Kiilunen is a Finnish music producer and entrepreneur best known as the founder of the classical and contemporary music label Ondine Records.
-
B.
Kalle Koskinen
Kalle Koskinen is a Finnish former professional ice hockey defenceman who played in the SM-liiga, notably for JYP Jyväskylä.
-
C.
Seppo Harjanne
Seppo Harjanne is a Finnish rally co-driver best known for partnering with top drivers such as Timo Salonen during the World Rally Championship era.
-
D.
Hannu Heikkinen
Hannu Heikkinen is a structural engineer known for his work on the design and construction of Toronto City Hall.
-
E.
Heikki Savolainen
Heikki Savolainen was a Finnish artistic gymnast and multiple Olympic medalist who became one of Finland’s most successful early 20th-century gymnasts.
- F. None of above. chosen
Provenance (5 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eefadeb56c8190bce79efadf3c644d |
completed | April 27, 2026, 5:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a3e5b04948190a62f3ed43ce115f0 |
completed | May 17, 2026, 10:16 p.m. |
| NEDg | Description generation | batch_6a0a3f0745b0819084e481b0b3cdf011 |
completed | May 17, 2026, 10:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a3fbeace48190874b808fd94d9e3c |
completed | May 17, 2026, 10:22 p.m. |
Created at: April 16, 2026, 6:32 p.m.