Triple

T13713497
Position Surface form Disambiguated ID Type / Status
Subject Levuka E328832 entity
Predicate hasLanguage P15 FINISHED
Object Fiji Hindi E41179 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: Fiji Hindi | Statement: [Levuka, hasLanguage, Fiji Hindi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fiji Hindi
Context triple: [Levuka, hasLanguage, Fiji Hindi]
  • A. Fiji Hindi chosen
    Fiji Hindi is an Indo-Aryan language spoken primarily by the Indo-Fijian community in Fiji, developed from dialects of North Indian languages brought by indentured laborers and influenced by English and Fijian.
  • B. Hindiyah
    Hindiyah is a town in Iraq, located in the Babil Governorate, known as the birthplace of former Prime Minister Nouri al-Maliki.
  • C. Andaman Hindi
    Andaman Hindi is a regional variety of Hindi that serves as a lingua franca among diverse communities in the Andaman Islands, including Great Andamanese speakers.
  • D. Hindko
    Hindko is a group of Indo-Aryan dialects spoken primarily in northern Pakistan, especially in parts of Khyber Pakhtunkhwa and Azad Kashmir.
  • E. Juang Bhasha
    Juang Bhasha is an endangered Munda language spoken by the Juang indigenous community in eastern India, primarily in the state of Odisha.
  • 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_69d80770b9bc81909f70c8c317d53cff completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dd4395e8c0819098719c8cd344aa33 completed April 13, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d56a90081908158dcf4ee061fb6 completed May 3, 2026, 7:09 p.m.
Created at: April 9, 2026, 9:54 p.m.