Triple
T4613149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Federer |
E100804
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mirka Federer |
E455726
|
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: Mirka Federer | Statement: [Roger Federer, spouse, Mirka Federer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mirka Federer Context triple: [Roger Federer, spouse, Mirka Federer]
-
A.
Miroslava Federer
chosen
Miroslava Federer is a former Slovak-born Swiss professional tennis player and the wife of tennis legend Roger Federer.
-
B.
Lara Gut-Behrami
Lara Gut-Behrami is a Swiss World Cup alpine ski racer and Olympic champion known for her success in speed events such as super-G and downhill.
-
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.
Vanessa Nadal
Vanessa Nadal is a chemical engineer and lawyer who works in intellectual property law and is married to composer and playwright Lin-Manuel Miranda.
-
E.
Monika Henreid
Monika Henreid is the daughter of classic Hollywood actor and director Paul Henreid, known for his roles in films such as "Casablanca" and "Now, Voyager."
- 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_69bd43cf363c819087fd5ab441b4a3f4 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd59c11f5481909f61e23503711cf5 |
completed | March 20, 2026, 2:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be035629248190a8723b5f1f9e57bc |
completed | March 21, 2026, 2:32 a.m. |
Created at: March 20, 2026, 1:12 p.m.