Triple
T17567966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tappara |
E427864
|
entity |
| Predicate | notableFormerCoach |
P4378
|
FINISHED |
| Object |
Jussi Tapola
Jussi Tapola is a Finnish ice hockey coach best known for leading Tappara to multiple Finnish Liiga championships.
|
E1280980
|
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: Jussi Tapola | Statement: [Tappara, notableFormerCoach, Jussi Tapola]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jussi Tapola Context triple: [Tappara, notableFormerCoach, Jussi Tapola]
-
A.
Jussi Pajunen
Jussi Pajunen is a Finnish politician and former Mayor of Helsinki who oversaw the city during major international events and urban development projects.
-
B.
Jussi Jääskeläinen
Jussi Jääskeläinen is a Finnish former professional goalkeeper best known for his long and distinguished spell at Bolton Wanderers in the English Premier League.
-
C.
Jussi Pakkanen
Jussi Pakkanen is a Finnish software developer best known as the original author of the Meson build system.
-
D.
Jaakko Lehtinen
Jaakko Lehtinen is a computer graphics and machine learning researcher known for his influential work on generative models and neural rendering techniques.
-
E.
Tapio Pulkkanen
Tapio Pulkkanen is a Finnish professional golfer known for competing on the European Tour.
- 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: Jussi Tapola Triple: [Tappara, notableFormerCoach, Jussi Tapola]
Generated description
Jussi Tapola is a Finnish ice hockey coach best known for leading Tappara to multiple Finnish Liiga championships.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jussi Tapola Target entity description: Jussi Tapola is a Finnish ice hockey coach best known for leading Tappara to multiple Finnish Liiga championships.
-
A.
Jussi Pajunen
Jussi Pajunen is a Finnish politician and former Mayor of Helsinki who oversaw the city during major international events and urban development projects.
-
B.
Jussi Jääskeläinen
Jussi Jääskeläinen is a Finnish former professional goalkeeper best known for his long and distinguished spell at Bolton Wanderers in the English Premier League.
-
C.
Jussi Pakkanen
Jussi Pakkanen is a Finnish software developer best known as the original author of the Meson build system.
-
D.
Jaakko Lehtinen
Jaakko Lehtinen is a computer graphics and machine learning researcher known for his influential work on generative models and neural rendering techniques.
-
E.
Tapio Pulkkanen
Tapio Pulkkanen is a Finnish professional golfer known for competing on the European Tour.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4592e56e481909249b831cecc31d5 |
completed | April 19, 2026, 4:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0216429964819081cc28582a87832d |
completed | May 11, 2026, 5:47 p.m. |
| NEDg | Description generation | batch_6a0217eee47881909a61527d4ce7bd54 |
completed | May 11, 2026, 5:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0218636e048190a48bc7f066c7bee1 |
completed | May 11, 2026, 5:56 p.m. |
Created at: April 10, 2026, 5:50 a.m.