Triple
T15905202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary-Kate Olsen |
E385693
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Olivier Sarkozy |
E986863
|
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: Olivier Sarkozy | Statement: [Mary-Kate Olsen, spouse, Olivier Sarkozy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olivier Sarkozy Context triple: [Mary-Kate Olsen, spouse, Olivier Sarkozy]
-
A.
Olivier Sarkozy
chosen
Olivier Sarkozy is a French-American investment banker best known for his work in the financial sector and his former marriage to fashion designer Mary-Kate Olsen.
-
B.
Nicolas Sarkozy
Nicolas Sarkozy is a French conservative politician who served as President of France from 2007 to 2012 and played a prominent role in European and international diplomacy.
-
C.
Laurence Chirac
Laurence Chirac was a French dentist and the eldest daughter of former French President Jacques Chirac.
-
D.
François Fillon
François Fillon is a French conservative politician who served as Prime Minister of France from 2007 to 2012 under President Nicolas Sarkozy.
-
E.
François Hollande
François Hollande is a French Socialist politician who served as President of France from 2012 to 2017.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1565956588190ba4726a2879b677d |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb0535a808190983b4ff028826cbf |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.