Triple
T15042804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mireille |
E378642
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Clémence |
E1002182
|
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: Clémence | Statement: [Mireille, mainCharacter, Clémence]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clémence Context triple: [Mireille, mainCharacter, Clémence]
-
A.
Clémence
chosen
Clémence is the given name of Jeanne Clémence Weil, best known as the mother of French writer Marcel Proust.
-
B.
Bénédicte
Bénédicte is the given name of Louise Bénédicte de Bourbon, a French noblewoman of the House of Bourbon.
-
C.
Geneviève
Geneviève is a character in Claude Debussy’s opera "Pelléas et Mélisande," typically portrayed as the mother of Pelléas and Golaud and a figure of quiet, dignified authority within the story.
-
D.
Françoise
Françoise is the given name of Louise de La Vallière, a 17th-century French noblewoman best known as a mistress of King Louis XIV.
-
E.
Françoise
Françoise is a French feminine given name historically borne by numerous notable women in France and other Francophone regions.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded82f73208190bb55fa6b20074e27 |
completed | April 15, 2026, 12:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fef888a7988190837f3f4b8d340e04 |
completed | May 9, 2026, 9:04 a.m. |
Created at: April 10, 2026, 3 a.m.