Triple

T16383949
Position Surface form Disambiguated ID Type / Status
Subject French colonial law E397874 entity
Predicate appliedIn P1129 FINISHED
Object French Madagascar E27635 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 Madagascar | Statement: [French colonial law, appliedIn, French Madagascar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: French Madagascar
Context triple: [French colonial law, appliedIn, French Madagascar]
  • A. French Guinea
    French Guinea was a former French colonial territory in West Africa that later became the independent nation of Guinea.
  • B. Réunion
    Réunion is a French island and overseas department in the Indian Ocean known for its volcanic landscapes, multicultural population, and status as an outermost region of the European Union.
  • C. Mauritius
    Mauritius is an island nation in the Indian Ocean known for its multicultural society, stable democracy, and tourism-driven economy.
  • D. Mauricius
    Mauricius is a Latin given name of Roman origin that later evolved into various European forms such as Maurice and Morris.
  • E. Madagascar chosen
    Madagascar is a large island nation in the Indian Ocean renowned for its unique biodiversity and high rate of endemic species.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319de83248190b5d43646fa9b6cda completed April 18, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00356b00408190beab51a23011be67 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.