Triple
T16019949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henrik Zetterberg |
E388572
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Emma Andersson
Emma Andersson is known as the spouse of Swedish ice hockey star Henrik Zetterberg.
|
E1192642
|
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: Emma Andersson | Statement: [Henrik Zetterberg, spouse, Emma Andersson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emma Andersson Context triple: [Henrik Zetterberg, spouse, Emma Andersson]
-
A.
Emma Nilsson
Emma Nilsson is a person bearing the Swedish surname Nilsson, which is common in Scandinavian countries.
-
B.
Ylva Johansson
Ylva Johansson is a Swedish politician who has served as European Commissioner for Home Affairs and previously held several ministerial posts in the Swedish government.
-
C.
Åsa Larsson
Åsa Larsson is a Swedish crime fiction author best known for her Rebecka Martinsson series set in northern Sweden.
-
D.
Maria Nilsson
Maria Nilsson is an archaeologist known for directing research and excavations at the ancient Egyptian site of Gebel el-Silsila.
-
E.
Kristina Edström
Kristina Edström is a Swedish chemist and professor renowned for her research on battery technology and energy storage materials.
- 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: Emma Andersson Triple: [Henrik Zetterberg, spouse, Emma Andersson]
Generated description
Emma Andersson is known as the spouse of Swedish ice hockey star Henrik Zetterberg.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Emma Andersson Target entity description: Emma Andersson is known as the spouse of Swedish ice hockey star Henrik Zetterberg.
-
A.
Emma Nilsson
Emma Nilsson is a person bearing the Swedish surname Nilsson, which is common in Scandinavian countries.
-
B.
Ylva Johansson
Ylva Johansson is a Swedish politician who has served as European Commissioner for Home Affairs and previously held several ministerial posts in the Swedish government.
-
C.
Åsa Larsson
Åsa Larsson is a Swedish crime fiction author best known for her Rebecka Martinsson series set in northern Sweden.
-
D.
Maria Nilsson
Maria Nilsson is an archaeologist known for directing research and excavations at the ancient Egyptian site of Gebel el-Silsila.
-
E.
Kristina Edström
Kristina Edström is a Swedish chemist and professor renowned for her research on battery technology and energy storage materials.
- 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_69d86dabcb7c8190b6a39d6831d2fa1b |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e183222e4c81909a3ab51446b671bd |
completed | April 17, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe47280448190923a36e9a41ce7bc |
completed | May 10, 2026, 1:50 a.m. |
| NEDg | Description generation | batch_69ffe517c8f081908a1275d0adf3053d |
completed | May 10, 2026, 1:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffe572be388190bb492b6f554ec808 |
completed | May 10, 2026, 1:54 a.m. |
Created at: April 10, 2026, 4:55 a.m.