Triple
T16379141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vivian Oparah |
E397753
|
entity |
| Predicate | coStarredWith |
P14987
|
FINISHED |
| Object |
David Jonsson
David Jonsson is a British actor best known for his roles in the TV series "Industry" and the romantic film "Rye Lane."
|
E1214208
|
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: David Jonsson | Statement: [Vivian Oparah, coStarredWith, David Jonsson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Jonsson Context triple: [Vivian Oparah, coStarredWith, David Jonsson]
-
A.
Patrick Jonsson
Patrick Jonsson is a film composer known for his evocative scores for documentaries and independent films.
-
B.
Leo Danius Jonsson
Leo Danius Jonsson is the son of the late Swedish literary scholar and former Nobel Prize in Literature permanent secretary Sara Danius.
-
C.
Johannes Haukur Johannesson
Johannes Haukur Johannesson is an Icelandic actor known for his roles in international film and television productions, including action and fantasy projects.
-
D.
Sveinn Björnsson
Sveinn Björnsson was an Icelandic politician and diplomat who became the country's first president following its independence from Denmark.
-
E.
Magnus Haroldson
Magnus Haroldson was a son of Edith Swannesha, the longtime consort of King Harold Godwinson of England in the 11th century.
- 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: David Jonsson Triple: [Vivian Oparah, coStarredWith, David Jonsson]
Generated description
David Jonsson is a British actor best known for his roles in the TV series "Industry" and the romantic film "Rye Lane."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David Jonsson Target entity description: David Jonsson is a British actor best known for his roles in the TV series "Industry" and the romantic film "Rye Lane."
-
A.
Patrick Jonsson
Patrick Jonsson is a film composer known for his evocative scores for documentaries and independent films.
-
B.
Leo Danius Jonsson
Leo Danius Jonsson is the son of the late Swedish literary scholar and former Nobel Prize in Literature permanent secretary Sara Danius.
-
C.
Johannes Haukur Johannesson
Johannes Haukur Johannesson is an Icelandic actor known for his roles in international film and television productions, including action and fantasy projects.
-
D.
Sveinn Björnsson
Sveinn Björnsson was an Icelandic politician and diplomat who became the country's first president following its independence from Denmark.
-
E.
Magnus Haroldson
Magnus Haroldson was a son of Edith Swannesha, the longtime consort of King Harold Godwinson of England in the 11th century.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e319da3c6c8190a9ccf744996c31e8 |
completed | April 18, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00457751208190b1e3dd6be3c0f363 |
completed | May 10, 2026, 8:44 a.m. |
| NEDg | Description generation | batch_6a0046b4f6c88190b9cf4cb669b1b08a |
completed | May 10, 2026, 8:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a004a9d01a48190ad59b260980323cd |
completed | May 10, 2026, 9:06 a.m. |
Created at: April 10, 2026, 5:08 a.m.