Triple

T6638040
Position Surface form Disambiguated ID Type / Status
Subject Ngaju language E150506 entity
Predicate hasAlternativeName P39 FINISHED
Object Dayak Ngaju E542867 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: Dayak Ngaju | Statement: [Ngaju language, hasAlternativeName, Dayak Ngaju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dayak Ngaju
Context triple: [Ngaju language, hasAlternativeName, Dayak Ngaju]
  • A. Kayan Mahakam
    Kayan Mahakam is a regional variety of the Kayan language spoken by Kayan communities living along the Mahakam River in Indonesian Borneo.
  • B. Ngaju Dayak chosen
    Ngaju Dayak are an indigenous Dayak ethnic group of Central Kalimantan, Borneo, known for their distinct language, river-based settlements, and rich traditional culture and rituals.
  • C. Muara Bulian
    Muara Bulian is a town in Jambi Province on the island of Sumatra, Indonesia, known as an administrative and economic center in the Batang Hari Regency.
  • D. Kapuas River
    The Kapuas River is the longest river in Indonesia and one of the major waterways of Borneo, flowing through dense tropical rainforest and supporting rich biodiversity and local communities.
  • E. Watampone
    Watampone is the main urban and administrative center of Bone Regency in South Sulawesi, Indonesia.
  • 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_69c687f0ceb08190bf40807bfc605fa5 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6aff082b0819089f5a69aa67d5346 completed March 27, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6e453cb14819093597dda825b4304 completed March 27, 2026, 8:10 p.m.
Created at: March 27, 2026, 2 p.m.