Triple

T9896065
Position Surface form Disambiguated ID Type / Status
Subject Bajawa E182175 entity
Predicate isPartOf P10 FINISHED
Object Ngada Regency E658091 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: Ngada Regency | Statement: [Bajawa, isPartOf, Ngada Regency]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ngada Regency
Context triple: [Bajawa, isPartOf, Ngada Regency]
  • A. Ngada Regency chosen
    Ngada Regency is an administrative region on Flores Island in East Nusa Tenggara, Indonesia, known for its coastal landscapes, traditional villages, and marine attractions such as the Riung 17 Islands.
  • B. The Istana
    The Istana is the official presidential palace and primary ceremonial venue of Singapore, serving as the office and residence of the President.
  • C. Wawona Hotel
    Wawona Hotel is a historic Victorian-era lodge located in Yosemite National Park, known for its classic architecture and scenic mountain setting.
  • D. Nusantara Building
    The Nusantara Building is the iconic main plenary hall of Indonesia’s national parliament located in the Senayan area of Jakarta.
  • E. Nusa Dua
    Nusa Dua is a high-end resort area on the southern coast of Bali, Indonesia, known for its luxury hotels, beaches, and conference facilities.
  • 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_69ca82876f8081909cf75df0f99bb13f completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb4a9d2f4819086cfdd42b613cd8c completed April 2, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1eb1355888190baf9846815801e92 completed April 5, 2026, 4:54 a.m.
Created at: March 30, 2026, 8:39 p.m.