Triple

T5612946
Position Surface form Disambiguated ID Type / Status
Subject Maromokotro E147401 entity
Predicate nameLanguage P15 FINISHED
Object Malagasy E147397 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: Malagasy | Statement: [Maromokotro, nameLanguage, Malagasy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malagasy
Context triple: [Maromokotro, nameLanguage, Malagasy]
  • A. Malagasy chosen
    Malagasy is an Austronesian language spoken predominantly in Madagascar and serves as a key marker of the island’s national identity and culture.
  • B. Betsileo Malagasy
    Betsileo Malagasy is a prominent regional variety of the Malagasy language spoken primarily by the Betsileo people in the central highlands of Madagascar.
  • C. Sakalava Malagasy
    Sakalava Malagasy is a regional variety of the Malagasy language spoken primarily by the Sakalava people of western Madagascar.
  • D. Antandroy Malagasy
    Antandroy Malagasy is a regional variety of the Malagasy language spoken primarily by the Antandroy people in southern Madagascar.
  • E. Comorian language
    Comorian is a Bantu language spoken primarily in the Comoros Islands, closely related to Swahili and used in several regional varieties.
  • 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_69c00905d4588190bd967842bbcf2219 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0212143708190b5234407334ab216 completed March 22, 2026, 5:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69c097cc15348190b4db6db00f9b9faf completed March 23, 2026, 1:30 a.m.
Created at: March 22, 2026, 3:39 p.m.