Triple

T19856215
Position Surface form Disambiguated ID Type / Status
Subject Le Mortainais E477138 entity
Predicate containsAdministrativeTerritorialEntity P747 FINISHED
Object Sourdeval 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: Sourdeval | Statement: [Le Mortainais, containsAdministrativeTerritorialEntity, Sourdeval]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sourdeval
Context triple: [Le Mortainais, containsAdministrativeTerritorialEntity, Sourdeval]
  • A. Sourdeval chosen
    Sourdeval is a commune in the Manche department of northwestern France, known for its rural Norman landscape and traditional architecture.
  • B. Venteuil
    Venteuil is a small commune in the Marne department of northeastern France, known historically as the place where physicist Armand Fizeau died.
  • C. Casseneuil
    Casseneuil is a small commune in southwestern France, located in the Lot-et-Garonne department in the Nouvelle-Aquitaine region.
  • D. Savoleyres
    Savoleyres is a ski area in the Swiss Alps known for its slopes and lift connections between the resorts of Verbier and La Tzoumaz.
  • E. Vaujours
    Vaujours is a small suburban commune in the northeastern outskirts of Paris, France.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6586c14fc81908d34785f1088b0a9 completed April 20, 2026, 4:46 p.m.
Created at: April 10, 2026, 1:51 p.m.