Triple

T13841688
Position Surface form Disambiguated ID Type / Status
Subject Le Triomphe de la République E332672 entity
Predicate depicts P1581 FINISHED
Object Marianne E406303 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: Marianne | Statement: [Le Triomphe de la République, depicts, Marianne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marianne
Context triple: [Le Triomphe de la République, depicts, Marianne]
  • A. Marianne chosen
    Marianne is the national personification of the French Republic, symbolizing liberty, reason, and the values of the nation.
  • B. Marianne
    Marianne is a feminine given name of French origin that has been widely used in various cultures and is often associated with grace and classic elegance.
  • C. Marianne
    Marianne was a 19th-century Dutch princess of the House of Orange-Nassau, known for her independent spirit, unconventional personal life, and extensive patronage of the arts and architecture.
  • D. Marianne
    Marianne is the central female figure addressed in Leonard Cohen's song "So Long, Marianne," widely recognized as a muse-like character in his work.
  • E. Marianne
    Marianne is the central protagonist of the horror film "In Fabric," whose experiences with a cursed red dress drive the movie's surreal and unsettling narrative.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02ae5e4c8190ad85ad2968bc71b2 completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c0ef9e7c8190b96c2b83d04708e1 completed May 3, 2026, 9:41 p.m.
Created at: April 9, 2026, 10:13 p.m.