Triple
T9381523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marc Gisin |
E225794
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Michelle Gisin |
E229326
|
NE FINISHED |
How this triple was built (2 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: Michelle Gisin | Statement: [Marc Gisin, sibling, Michelle Gisin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michelle Gisin Context triple: [Marc Gisin, sibling, Michelle Gisin]
-
A.
Michelle Gisin
chosen
Michelle Gisin is a Swiss alpine ski racer and Olympic champion known for her success in multiple World Cup disciplines.
-
B.
Marc Gisin
Marc Gisin is a Swiss former World Cup alpine ski racer known primarily as a speed specialist in downhill and super-G events.
-
C.
Dominique Gisin
Dominique Gisin is a Swiss alpine ski racer best known for winning the gold medal in the women's downhill at the 2014 Winter Olympics in Sochi.
-
D.
Dominique Engerer
Dominique Engerer was a renowned French classical pianist celebrated for her expressive interpretations and international concert career.
-
E.
Denise Berthoud
Denise Berthoud was a notable Swiss figure, likely recognized for significant cultural or public contributions that merited burial in Geneva’s prestigious Cimetière des Rois.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca842e9dcc8190a264119e683cfe04 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd50be52248190bc7cd9deb95a1ef8 |
completed | April 1, 2026, 5:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1525e54c8819080e731668b1eb8c8 |
completed | April 4, 2026, 6:03 p.m. |
Created at: March 30, 2026, 7:44 p.m.