Triple

T16892020
Position Surface form Disambiguated ID Type / Status
Subject La Maison Jaune E424196 entity
Predicate shortName P43 FINISHED
Object Maison Jaune E185575 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: Maison Jaune | Statement: [La Maison Jaune, shortName, Maison Jaune]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maison Jaune
Context triple: [La Maison Jaune, shortName, Maison Jaune]
  • A. Maison Jaune chosen
    Maison Jaune is the famous house in Arles where Vincent van Gogh lived and created some of his most iconic paintings.
  • B. Maison Blanche
    Maison Blanche is a Paris Métro station in the 13th arrondissement, serving as a stop on the city's Line 7.
  • C. La Maison Jaune
    La Maison Jaune is a popular nickname for the French football club FC Nantes, referencing its iconic yellow team colors.
  • D. Maison Autrique
    Maison Autrique is an early Art Nouveau townhouse in Schaerbeek, Brussels, designed by architect Victor Horta and noted as a key milestone in his architectural career.
  • E. Maison-Rouge
    Maison-Rouge is a French commune in the Seine-et-Marne department in the Île-de-France region of north-central France.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3bbc5a5308190937ebd05356bd91d completed April 18, 2026, 5:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2c414b081909b98e40ee9a176e2 completed May 10, 2026, 5:39 p.m.
Created at: April 10, 2026, 5:29 a.m.