Triple

T7855633
Position Surface form Disambiguated ID Type / Status
Subject Gilimanuk E182167 entity
Predicate connectsTo P845 FINISHED
Object Ketapang E169314 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: Ketapang | Statement: [Gilimanuk, connectsTo, Ketapang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ketapang
Context triple: [Gilimanuk, connectsTo, Ketapang]
  • A. Ketapang chosen
    Ketapang is a key ferry port town in East Java, Indonesia, serving as a primary gateway for sea crossings between Java and Bali.
  • B. Padang Besar
    Padang Besar is a border town in northern Malaysia known as a key land gateway and trading hub between Malaysia and Thailand.
  • C. Singkawang
    Singkawang is a city in West Kalimantan, Indonesia, known for its large Chinese Indonesian community and vibrant Chinese cultural festivals, especially its Cap Go Meh celebrations.
  • D. Keningau
    Keningau is a major inland town and administrative district in the interior region of the Malaysian state of Sabah.
  • E. Tenggarong
    Tenggarong is a town in East Kalimantan, Indonesia, that serves as the capital of Kutai Kartanegara Regency and a cultural center of the historic Kutai region.
  • 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_69ca82869ee08190b8f9040dbc2c0467 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb1a74592c8190b42f298e3e33617b completed March 31, 2026, 12:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b2e2980819083369668938bae9c completed March 31, 2026, 5:27 a.m.
Created at: March 30, 2026, 4:52 p.m.