Triple
T562324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Letizia Ramolino |
E13478
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | Maria Lætitia Ramolino |
E13478
|
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: Maria Lætitia Ramolino | Statement: [Letizia Ramolino, nativeName, Maria Lætitia Ramolino]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maria Lætitia Ramolino Context triple: [Letizia Ramolino, nativeName, Maria Lætitia Ramolino]
-
A.
Letizia Ramolino
chosen
Letizia Ramolino was a Corsican noblewoman best known as the mother of French Emperor Napoleon Bonaparte and a matriarch of the Bonaparte family.
-
B.
Paola Ruffo di Calabria
Paola Ruffo di Calabria is the Italian-born former Queen of the Belgians, wife of King Albert II and mother of King Philippe.
-
C.
Eugénie Savoye
Eugénie Savoye was a French client and member of the Savoye family who commissioned Le Corbusier to design the iconic modernist Villa Savoye.
-
D.
Anne Martel
Anne Martel is a Canadian entrepreneur and co-founder of the artificial intelligence company Element AI.
-
E.
Hortense Fiquet
Hortense Fiquet was a French model best known as the wife and frequent portrait subject of the painter Paul Cézanne.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49a700e608190b235246df057bd9b |
completed | March 1, 2026, 7:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a6373fbf388190afb01fcfd67f03bf |
completed | March 3, 2026, 1:19 a.m. |
Created at: March 1, 2026, 7:32 p.m.