Triple

T20797628
Position Surface form Disambiguated ID Type / Status
Subject Karo Regency E511952 entity
Predicate regencySeat P71777 FINISHED
Object Kabanjahe 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: Kabanjahe | Statement: [Karo Regency, regencySeat, Kabanjahe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kabanjahe
Context triple: [Karo Regency, regencySeat, Kabanjahe]
  • A. Kabanjahe chosen
    Kabanjahe is a principal town and administrative center in North Sumatra, Indonesia, known as a hub of Karo culture and gateway to the surrounding highland region.
  • B. Kaltungo
    Kaltungo is a town and administrative center in northeastern Nigeria known for its role as one of the local government areas within Gombe State.
  • C. Barawa
    Barawa is a historic coastal city in southern Somalia known as an important port and cultural center of the Bravanese people.
  • D. Barawa
    Barawa is a West Chadic language spoken in parts of Nigeria, belonging to the Afroasiatic language family.
  • E. Kumba
    Kumba is a major town in southwestern Cameroon known as a commercial hub and cultural crossroads where languages like Cameroonian Pidgin English are widely used.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2ae2c4c819087f620df31dc1aba completed April 21, 2026, 12:19 a.m.
Created at: April 16, 2026, 12:39 p.m.