Triple

T2900396
Position Surface form Disambiguated ID Type / Status
Subject Foreign Legion E62639 entity
Predicate garrison P75 FINISHED
Object French Guiana E29075 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: French Guiana | Statement: [Foreign Legion, garrison, French Guiana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: French Guiana
Context triple: [Foreign Legion, garrison, French Guiana]
  • A. French Guiana chosen
    French Guiana is a sparsely populated territory on the northeastern coast of South America known for its Amazonian rainforest and the European spaceport at Kourou.
  • B. French Guinea
    French Guinea was a former French colonial territory in West Africa that later became the independent nation of Guinea.
  • C. Guadeloupe
    Guadeloupe is a Caribbean archipelago that forms an overseas region and department of France, known for its blend of French and Creole culture, volcanic landscapes, and beaches.
  • D. Guianas
    The Guianas is a region on the northeastern coast of South America comprising Guyana, Suriname, French Guiana, and sometimes adjacent areas, known for its dense rainforests and cultural diversity.
  • E. Martinique
    Martinique is a Caribbean island and French overseas region known for its blend of French and Creole culture, volcanic landscapes, and beaches.
  • 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_69ab4c3e070c8190b78d3d2c005876dd completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abe0b081308190af8875151fb11c4e completed March 7, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69b0318f2c908190aa10aa93f8fb139c completed March 10, 2026, 2:58 p.m.
Created at: March 6, 2026, 10:10 p.m.