Triple

T2960960
Position Surface form Disambiguated ID Type / Status
Subject Manado E80045 entity
Predicate near P350 FINISHED
Object Bunaken Island E312520 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: Bunaken Island | Statement: [Manado, near, Bunaken Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bunaken Island
Context triple: [Manado, near, Bunaken Island]
  • A. Bunaken National Park chosen
    Bunaken National Park is a renowned marine reserve in Indonesia celebrated for its exceptional coral reefs, rich biodiversity, and world-class scuba diving.
  • B. Sipadan Island
    Sipadan Island is a renowned Malaysian oceanic island in the Celebes Sea, famous for its rich marine biodiversity and world-class scuba diving sites.
  • C. Buru Island
    Buru Island is a remote Indonesian island in the Maluku province, historically notorious as a political prison camp site during the Suharto era.
  • D. Baluan Island
    Baluan Island is a small volcanic island in Papua New Guinea’s Admiralty Islands, known for its traditional Manus culture and surrounding coral reefs.
  • E. Buton Island
    Buton Island is a large island in Southeast Sulawesi, Indonesia, known for its diverse indigenous cultures and languages as well as its strategic location along historic maritime trade routes.
  • 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_69ad8b1341848190bd19dbf46892887d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad995454448190834aa5d47a4ed5ac completed March 8, 2026, 3:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b37383fbf881909361d448de3c266b completed March 13, 2026, 2:16 a.m.
Created at: March 8, 2026, 2:57 p.m.