Triple
T1007909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacob Bjerknes |
E21754
|
entity |
| Predicate | notableStudent |
P4838
|
FINISHED |
| Object |
Arnt Eliassen
Arnt Eliassen was a prominent Norwegian meteorologist known for his influential work in dynamic meteorology and numerical weather prediction.
|
E130106
|
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: Arnt Eliassen | Statement: [Jacob Bjerknes, notableStudent, Arnt Eliassen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arnt Eliassen Context triple: [Jacob Bjerknes, notableStudent, Arnt Eliassen]
-
A.
Christian M. Ravndal
Christian M. Ravndal was an American diplomat who served as the United States Ambassador to Hungary.
-
B.
Lee Haugen
Lee Haugen is a film editor best known for his work on the adventure drama "The Lost City of Z."
-
C.
Johann Olav Koss
Johann Olav Koss is a Norwegian speed skater renowned for winning multiple gold medals and setting world records at the 1994 Lillehammer Winter Olympics.
-
D.
Jan Christian Vestre
Jan Christian Vestre is a Norwegian Labour Party politician and businessman who has served as Norway’s Minister of Trade and Industry.
-
E.
Peter Amundson
Peter Amundson is a film editor best known for his work on major Hollywood productions, including the science-fiction action film "Pacific Rim."
- 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: Arnt Eliassen Triple: [Jacob Bjerknes, notableStudent, Arnt Eliassen]
Generated description
Arnt Eliassen was a prominent Norwegian meteorologist known for his influential work in dynamic meteorology and numerical weather prediction.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Arnt Eliassen Target entity description: Arnt Eliassen was a prominent Norwegian meteorologist known for his influential work in dynamic meteorology and numerical weather prediction.
-
A.
Christian M. Ravndal
Christian M. Ravndal was an American diplomat who served as the United States Ambassador to Hungary.
-
B.
Lee Haugen
Lee Haugen is a film editor best known for his work on the adventure drama "The Lost City of Z."
-
C.
Johann Olav Koss
Johann Olav Koss is a Norwegian speed skater renowned for winning multiple gold medals and setting world records at the 1994 Lillehammer Winter Olympics.
-
D.
Jan Christian Vestre
Jan Christian Vestre is a Norwegian Labour Party politician and businessman who has served as Norway’s Minister of Trade and Industry.
-
E.
Peter Amundson
Peter Amundson is a film editor best known for his work on major Hollywood productions, including the science-fiction action film "Pacific Rim."
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7a2186c819081a495bc15f8c7fd |
completed | March 1, 2026, 10:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac5995ad6c8190a324094151442bce |
completed | March 7, 2026, 5 p.m. |
| NEDg | Description generation | batch_69ac5a2cae9881908a9cfc09f9ef0968 |
completed | March 7, 2026, 5:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac5b54d1f881909a367d12647eee3f |
completed | March 7, 2026, 5:07 p.m. |
Created at: March 1, 2026, 7:41 p.m.