Triple

T22175799
Position Surface form Disambiguated ID Type / Status
Subject Pakpak-Dairi E548045 entity
Predicate region P40 FINISHED
Object Dairi Regency NE NERFINISHED

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: Dairi Regency | Statement: [Pakpak-Dairi, region, Dairi Regency]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dairi Regency
Context triple: [Pakpak-Dairi, region, Dairi Regency]
  • A. Dairi Regency chosen
    Dairi Regency is an inland regency in North Sumatra, Indonesia, known for its highland terrain, coffee production, and proximity to Lake Toba.
  • B. Karo Regency
    Karo Regency is an administrative region in North Sumatra, Indonesia, known as the homeland of the Karo Batak people and their distinctive language and culture.
  • C. Malinau Regency
    Malinau Regency is an administrative region in northern Borneo known for its vast rainforest areas, rich indigenous Dayak cultures, and significant biodiversity.
  • D. Bulukumba Regency
    Bulukumba Regency is an administrative region in Indonesia known for its traditional wooden phinisi shipbuilding and coastal tourism, located at the southern tip of South Sulawesi.
  • E. Tebo Regency
    Tebo Regency is an administrative region in Jambi Province on the island of Sumatra, Indonesia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e3d53f88190a2b690e3f25bb062 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a6c40988190ba52ea46079eb306 completed April 28, 2026, 9:45 p.m.
Created at: April 16, 2026, 8:34 p.m.