Triple
T20496768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amanda Burton |
E502894
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Sven Arnstein
Sven Arnstein is a British photographer and television director best known for his marriage to actress Amanda Burton.
|
E1448044
|
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: Sven Arnstein | Statement: [Amanda Burton, spouse, Sven Arnstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sven Arnstein Context triple: [Amanda Burton, spouse, Sven Arnstein]
-
A.
Sven Palme
Sven Palme was a Swedish politician and lawyer, known as the grandfather of former Prime Minister Olof Palme and a prominent figure in early 20th-century Swedish public life.
-
B.
Karl Sodersten
Karl Sodersten is a film editor known for his work on the Australian psychological thriller "Lantana."
-
C.
Arne Hanna
Arne Hanna is a musician best known as a member of the Australian ambient/world music band Not Drowning, Waving.
-
D.
Arnold Eidus
Arnold Eidus was an American classical violinist and recording artist known for his virtuosity and work as a soloist and studio musician in the mid-20th century.
-
E.
Carl Skottsberg
Carl Skottsberg was a Swedish botanist and explorer renowned for his pioneering research on subantarctic and Antarctic flora.
- 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: Sven Arnstein Triple: [Amanda Burton, spouse, Sven Arnstein]
Generated description
Sven Arnstein is a British photographer and television director best known for his marriage to actress Amanda Burton.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sven Arnstein Target entity description: Sven Arnstein is a British photographer and television director best known for his marriage to actress Amanda Burton.
-
A.
Sven Palme
Sven Palme was a Swedish politician and lawyer, known as the grandfather of former Prime Minister Olof Palme and a prominent figure in early 20th-century Swedish public life.
-
B.
Karl Sodersten
Karl Sodersten is a film editor known for his work on the Australian psychological thriller "Lantana."
-
C.
Arne Hanna
Arne Hanna is a musician best known as a member of the Australian ambient/world music band Not Drowning, Waving.
-
D.
Arnold Eidus
Arnold Eidus was an American classical violinist and recording artist known for his virtuosity and work as a soloist and studio musician in the mid-20th century.
-
E.
Carl Skottsberg
Carl Skottsberg was a Swedish botanist and explorer renowned for his pioneering research on subantarctic and Antarctic flora.
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cbdeb9c819090a30a7961146c93 |
completed | April 20, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08e8234328819089fdf979d9a41bca |
completed | May 16, 2026, 9:56 p.m. |
| NEDg | Description generation | batch_6a08e8df60c88190803590abd75b3e43 |
completed | May 16, 2026, 9:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08e95f05088190b5934f067c5dd7b7 |
completed | May 16, 2026, 10:02 p.m. |
Created at: April 16, 2026, 11:35 a.m.