Triple

T22175804
Position Surface form Disambiguated ID Type / Status
Subject Pakpak-Dairi E548045 entity
Predicate hasDialects P4251 FINISHED
Object Pakpak Pegagan 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: Pakpak Pegagan | Statement: [Pakpak-Dairi, hasDialects, Pakpak Pegagan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pakpak Pegagan
Context triple: [Pakpak-Dairi, hasDialects, Pakpak Pegagan]
  • A. Pakpak Pegagan chosen
    Pakpak Pegagan is a regional dialect of the Pakpak Dairi language spoken by the Pakpak community in parts of North Sumatra, Indonesia.
  • B. Pringsewu
    Pringsewu is a town in Lampung Province on the Indonesian island of Sumatra, known as an administrative and commercial center for the surrounding Pringsewu Regency.
  • C. Tunggul Ametung
    Tunggul Ametung was a regional ruler in early 13th-century Java, best known from Javanese chronicles as the leader of Tumapel whose assassination enabled Ken Arok to rise to power and found the Singhasari kingdom.
  • D. Sesetan
    Sesetan is an urban village and administrative area within Denpasar, the capital city of Bali, Indonesia.
  • E. Gadong
    Gadong is a major commercial and entertainment hub in Brunei, known for its shopping centers, markets, and vibrant urban activity.
  • 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.