Triple

T7133840
Position Surface form Disambiguated ID Type / Status
Subject Dhivehi E166254 entity
Predicate hasDialect P4251 FINISHED
Object Addu dialect E637015 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: Addu dialect | Statement: [Dhivehi, hasDialect, Addu dialect]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Addu dialect
Context triple: [Dhivehi, hasDialect, Addu dialect]
  • A. Addu dialect chosen
    The Addu dialect is a regional variety of the Dhivehi language traditionally spoken in the Addu Atoll of the Maldives, known for its distinctive phonological and lexical features.
  • B. Doabi dialect
    The Doabi dialect is a regional variety of Punjabi traditionally spoken in the Doaba region of the Indian state of Punjab, between the Beas and Sutlej rivers.
  • C. Akusha dialect
    The Akusha dialect is a principal standardized variety of the Dargin language spoken in Dagestan, Russia.
  • D. Tappalang dialect
    The Tappalang dialect is a regional variety of the Mandar language spoken by Mandar communities in parts of West Sulawesi, Indonesia.
  • E. Sekopa dialect
    The Sekopa dialect is a regional variety of the Northern Sotho language spoken by specific communities in South Africa, distinguished by its own phonological and lexical features.
  • 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_69c68884a9388190af42f90d1c1a7151 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e68f15bc8190a4d82b8ee388f497 completed March 27, 2026, 8:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7a344fb4881908f6b6e33706e0192 completed March 28, 2026, 9:45 a.m.
Created at: March 27, 2026, 2:45 p.m.