Triple

T20767974
Position Surface form Disambiguated ID Type / Status
Subject Pawan River E511149 entity
Predicate hasMouthNear P350 FINISHED
Object Ketapang 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: Ketapang | Statement: [Pawan River, hasMouthNear, Ketapang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ketapang
Context triple: [Pawan River, hasMouthNear, Ketapang]
  • A. Ketapang
    Ketapang is a key ferry port town in East Java, Indonesia, serving as a primary gateway for sea crossings between Java and Bali.
  • B. Ketapang chosen
    Ketapang is a coastal town and regency capital in West Kalimantan, Indonesia, known for its role as a regional economic and transportation hub.
  • C. Sanggau
    Sanggau is a town and regency seat in the interior of West Kalimantan, Indonesia, known as an administrative and trading center along the Kapuas River.
  • D. Mempawah
    Mempawah is a coastal town and regency capital in Indonesian Borneo known for its river port, Malay cultural heritage, and role as an administrative center in West Kalimantan.
  • E. Sintang
    Sintang is a town and regency capital in the interior of West Kalimantan, Indonesia, situated near the confluence of the Kapuas and Melawi rivers.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c24df58c8190b37398353ce4bf24 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:36 p.m.