Triple
T9672972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zurbriggen |
E234073
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Heidi Zurbriggen
Heidi Zurbriggen is a former Swiss alpine skier who competed at the international level in the late 20th century.
|
E813953
|
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: Heidi Zurbriggen | Statement: [Zurbriggen, hasNotableBearer, Heidi Zurbriggen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heidi Zurbriggen Context triple: [Zurbriggen, hasNotableBearer, Heidi Zurbriggen]
-
A.
Maria Borgel
Maria Borgel is known as the wife of German film director Wolfgang Petersen.
-
B.
Daniella Pick
Daniella Pick is an Israeli singer and model who is married to American filmmaker Quentin Tarantino.
-
C.
Ifigenia Martínez
Ifigenia Martínez is a Mexican economist, diplomat, and left-wing politician best known as one of the founding figures of modern progressive politics in Mexico.
-
D.
Daniella Kertesz
Daniella Kertesz is an Israeli actress best known internationally for her role as an Israeli soldier alongside Brad Pitt in the zombie apocalypse film "World War Z."
-
E.
Daniela Andrade
Daniela Andrade is a Canadian singer-songwriter and YouTube artist known for her intimate acoustic covers and original indie-pop music.
- 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: Heidi Zurbriggen Triple: [Zurbriggen, hasNotableBearer, Heidi Zurbriggen]
Generated description
Heidi Zurbriggen is a former Swiss alpine skier who competed at the international level in the late 20th century.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Heidi Zurbriggen Target entity description: Heidi Zurbriggen is a former Swiss alpine skier who competed at the international level in the late 20th century.
-
A.
Maria Borgel
Maria Borgel is known as the wife of German film director Wolfgang Petersen.
-
B.
Daniella Pick
Daniella Pick is an Israeli singer and model who is married to American filmmaker Quentin Tarantino.
-
C.
Ifigenia Martínez
Ifigenia Martínez is a Mexican economist, diplomat, and left-wing politician best known as one of the founding figures of modern progressive politics in Mexico.
-
D.
Daniella Kertesz
Daniella Kertesz is an Israeli actress best known internationally for her role as an Israeli soldier alongside Brad Pitt in the zombie apocalypse film "World War Z."
-
E.
Daniela Andrade
Daniela Andrade is a Canadian singer-songwriter and YouTube artist known for her intimate acoustic covers and original indie-pop music.
- 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_69ca848f55e48190b3f67252571c3d45 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c6aa01c819083fc758470096ec2 |
completed | April 1, 2026, 10:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d18a2d030c8190ada52e855bc9afc8 |
completed | April 4, 2026, 10:01 p.m. |
| NEDg | Description generation | batch_69d18bf051448190aaa3a7198c23fd39 |
completed | April 4, 2026, 10:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d18c8783f08190858681b51096fe56 |
completed | April 4, 2026, 10:11 p.m. |
Created at: March 30, 2026, 8:15 p.m.