Triple
T21965858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Élisabeth Depardieu |
E542454
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Élisabeth |
—
|
NE NERFINISHED |
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: Élisabeth | Statement: [Élisabeth Depardieu, givenName, Élisabeth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Élisabeth Context triple: [Élisabeth Depardieu, givenName, Élisabeth]
-
A.
Élisabeth Marguerite
Élisabeth Marguerite d'Orléans was a 17th-century French princess of the blood, daughter of Gaston, Duke of Orléans, and a member of the House of Bourbon.
-
B.
Elisabeth
Elisabeth is a metro station on the Brussels Metro system in Brussels, Belgium.
-
C.
Elisabeth
chosen
Elisabeth is a feminine given name of Hebrew origin, commonly used in various European languages as a form of Elizabeth.
-
D.
Louise Marie Amélie
Louise Marie Amélie was a 19th-century Belgian princess, the eldest daughter of King Leopold II of Belgium and Queen Marie Henriette.
-
E.
Victoria of France
Victoria of France was a French princess, daughter of King Henry II and Catherine de' Medici, and sister of King Francis II of France.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c47fab1081908dc74a6545dbb051 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1245aabf88190a44564e6eaaa94ce |
completed | April 28, 2026, 9:19 p.m. |
Created at: April 16, 2026, 8:01 p.m.