Triple

T2976045
Position Surface form Disambiguated ID Type / Status
Subject West Sulawesi E80398 entity
Predicate hasCity P316 FINISHED
Object Mamuju E316096 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: Mamuju | Statement: [West Sulawesi, hasCity, Mamuju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mamuju
Context triple: [West Sulawesi, hasCity, Mamuju]
  • A. Mamuju chosen
    Mamuju is a coastal city on the island of Sulawesi in Indonesia known as an administrative and economic center in the region.
  • B. Ulsan
    Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
  • C. Gwangju
    Gwangju is a major metropolitan city in southwestern South Korea known for its rich cultural heritage and pivotal role in the country’s pro-democracy movement.
  • D. Uiwang
    Uiwang is a small inland city in South Korea known for its transportation infrastructure and proximity to Seoul.
  • E. Daejeon
    Daejeon is a major city in central South Korea known as a hub for science, technology, and research institutions.
  • 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_69ad8b15f6ac8190be5fd16a33edcb4f completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad998ad5308190a012ec4940eb46cb completed March 8, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e2c498881909dc0349b56db5c87 completed March 11, 2026, 8:56 a.m.
Created at: March 8, 2026, 2:58 p.m.