Triple

T19711597
Position Surface form Disambiguated ID Type / Status
Subject Elysette E473359 entity
Predicate namedAfter P63 FINISHED
Object Élysée Palace NE NERFINISHED

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: Élysée Palace | Statement: [Elysette, namedAfter, Élysée Palace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Élysée Palace
Context triple: [Elysette, namedAfter, Élysée Palace]
  • A. Élysée Palace chosen
    The Élysée Palace is the official seat and workplace of the President of France, located in central Paris and serving as a key center of French political power.
  • B. Hôtel de Matignon
    The Hôtel de Matignon is a historic Parisian mansion that serves as the official residence and workplace of the head of the French government.
  • C. Elysees
    "Elysees" is a track from Roddy Ricch's debut studio album "Please Excuse Me for Being Antisocial."
  • D. Goyon de Matignon
    Goyon de Matignon is a historic French noble surname associated with the influential Matignon family, prominent in the aristocracy of France and Monaco.
  • E. Palais fédéral
    Palais fédéral is the French name for Switzerland’s Federal Palace, the seat of the Swiss Federal Assembly and Federal Council in Bern.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e64408bde08190aa3bef8516491e03 completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.