Triple

T15817258
Position Surface form Disambiguated ID Type / Status
Subject Jhapa District E383510 entity
Predicate language P15 FINISHED
Object Bantawa E820722 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: Bantawa | Statement: [Jhapa District, language, Bantawa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bantawa
Context triple: [Jhapa District, language, Bantawa]
  • A. Bantawa Rai chosen
    Bantawa Rai are a subgroup of the Rai people of eastern Nepal, known for their distinct Bantawa language and rich Kirati cultural traditions.
  • B. Indrapura
    Indrapura was a prominent historical capital city of the Champa kingdom in what is now central Vietnam.
  • C. Hosapete
    Hosapete is a city in the Indian state of Karnataka, known as a gateway to the UNESCO World Heritage site of Hampi and for its proximity to major irrigation and hydroelectric projects on the Tungabhadra River.
  • D. Bundi
    Bundi is a historic city in Rajasthan, India, renowned for its ornate palaces, stepwells, and well-preserved medieval architecture.
  • E. Narangba
    Narangba is a residential suburb in the Moreton Bay region of Queensland, Australia, known for its family-friendly communities and semi-rural atmosphere.
  • 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_69d86da2858c819090cc8481e7207b6e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0c4a4332c8190bc525e06d6f3a6b4 completed April 16, 2026, 11:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9997e0048190b0c00a5a0ff561c9 completed May 9, 2026, 8:31 p.m.
Created at: April 10, 2026, 4:49 a.m.