Triple
T8500516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gigi Perreau |
E201203
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Ghislaine |
E450249
|
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: Ghislaine | Statement: [Gigi Perreau, givenName, Ghislaine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ghislaine Context triple: [Gigi Perreau, givenName, Ghislaine]
-
A.
Ghislaine
chosen
Ghislaine is a given name of French origin, used as one of the personal names of Mathilde Marie Christine Ghislaine d’Udekem d’Acoz, the Queen of the Belgians.
-
B.
Jeanne Samary
Jeanne Samary was a French actress at the Comédie-Française and a frequent model for Impressionist painter Pierre-Auguste Renoir.
-
C.
Camille Lefèvre
Camille Lefèvre was a Swiss architect best known for co-designing the Palais des Nations, the former League of Nations headquarters in Geneva.
-
D.
Michèle
Michèle is a feminine given name of French origin, commonly used in French-speaking countries.
-
E.
Ghislaine Elizabeth Marie Thérèse Perreau-Saussine
Ghislaine Elizabeth Marie Thérèse Perreau-Saussine, better known as Gigi Perreau, is an American former child actress who became a prominent film and television performer in the 1940s and 1950s.
- 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_69ca831fe47c8190b5c57b456d2aefa0 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5996ce88190956cb3f8d9ad3daf |
completed | March 31, 2026, 3:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce88e0e08c819085d29157349a6ef6 |
completed | April 2, 2026, 3:18 p.m. |
Created at: March 30, 2026, 6:14 p.m.