Triple

T1883192
Position Surface form Disambiguated ID Type / Status
Subject Marie-Louise E39898 entity
Predicate hasVariant P455 FINISHED
Object Marie Louise E39898 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: Marie Louise | Statement: [Marie-Louise, hasVariant, Marie Louise]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marie Louise
Context triple: [Marie-Louise, hasVariant, Marie Louise]
  • A. Marie Louise of France
    Marie Louise of France was a French princess, the short-lived eldest daughter of King Louis XV and Queen Marie Leszczyńska, who died in early childhood.
  • B. Marie Louise of Hesse-Kassel
    Marie Louise of Hesse-Kassel was a German noblewoman who became Princess of Orange and an influential matriarch of the House of Orange-Nassau in the early 18th century.
  • C. Marie-Louise chosen
    Marie-Louise is a feminine given name of French origin, often associated with European nobility and historical figures.
  • D. Marie Louise, Duchess of Parma
    Marie Louise, Duchess of Parma, was an Austrian archduchess and the second wife of Napoleon Bonaparte who later ruled Parma, Piacenza, and Guastalla in her own right.
  • E. Marie-Thérèse
    Marie-Thérèse is a French given name, famously borne by Marie-Thérèse Walter, a muse and lover of Pablo Picasso.
  • 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_69a88633e4fc8190b7eb40463e048ec5 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0fd4d6881908b8266bdae1517ce completed March 7, 2026, 5 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71a242f081908179251c120dd229 completed March 9, 2026, 7:07 a.m.
Created at: March 4, 2026, 7:34 p.m.