Triple

T19495997
Position Surface form Disambiguated ID Type / Status
Subject Matra E487771 entity
Predicate hasSubsidiary P254 FINISHED
Object Matra Défense 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: Matra Défense | Statement: [Matra, hasSubsidiary, Matra Défense]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matra Défense
Context triple: [Matra, hasSubsidiary, Matra Défense]
  • A. Traton
    Traton is a commercial vehicle manufacturer and holding company that oversees brands like MAN and Scania within the Volkswagen Group.
  • B. Renault
    Renault is a major French automobile manufacturer known for producing a wide range of passenger cars, commercial vehicles, and electric vehicles sold worldwide.
  • C. Peugeot
    Peugeot is a historic French automobile manufacturer known for producing a wide range of passenger cars and commercial vehicles, now operating as a core brand within the multinational automotive group Stellantis.
  • D. Matra Automobiles chosen
    Matra Automobiles was a French car manufacturer best known for its innovative sports cars and collaborations with brands like Renault and Simca during the late 20th century.
  • E. Saint-Chamond
    Saint-Chamond is an industrial town in central France known historically for its steelworks and armaments production, particularly during the 19th and early 20th centuries.
  • 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_69d8e8d9d1c88190b01cd78b8be49384 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6349182ec81908dd301f802530eec completed April 20, 2026, 2:13 p.m.
Created at: April 10, 2026, 1:40 p.m.