Triple

T11941377
Position Surface form Disambiguated ID Type / Status
Subject A Trip to the Moon E284184 entity
Predicate starred P5563 FINISHED
Object Jeanne d’Alcy E955129 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: Jeanne d’Alcy | Statement: [A Trip to the Moon, starred, Jeanne d’Alcy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeanne d’Alcy
Context triple: [A Trip to the Moon, starred, Jeanne d’Alcy]
  • A. Jeanne d’Alcy chosen
    Jeanne d’Alcy was a pioneering French stage and film actress, best known as one of the earliest film performers and a frequent collaborator in Georges Méliès’s groundbreaking silent films.
  • B. Jeanne de Dammartin
    Jeanne de Dammartin was a 13th-century French noblewoman who became Queen consort of Castile and León through her marriage to King Ferdinand III.
  • C. Jeanne de Batarnay
    Jeanne de Batarnay was a French noblewoman of the early 16th century best known as the mother of Diane de Poitiers, the influential mistress of King Henry II of France.
  • D. Jeanne d’Hauteserre
    Jeanne d’Hauteserre is a French politician who serves as the mayor of Paris’s affluent 8th arrondissement.
  • E. Geneviève de Séréville
    Geneviève de Séréville was a French woman best known as one of the wives of playwright and filmmaker Sacha Guitry.
  • 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_69d6ab2db38c8190b1f0ed6663ef8ada completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d90342bb908190a019ac91a2b82f3d completed April 10, 2026, 2:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69f458b9a35c8190875cb5ac7c9bcfba completed May 1, 2026, 7:39 a.m.
Created at: April 8, 2026, 9:45 p.m.