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.