Triple

T2333725
Position Surface form Disambiguated ID Type / Status
Subject Pontianak E44262 entity
Predicate partOf P40 FINISHED
Object Kalimantan E79483 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: Kalimantan | Statement: [Pontianak, partOf, Kalimantan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kalimantan
Context triple: [Pontianak, partOf, Kalimantan]
  • A. Kalimantan chosen
    Kalimantan is the Indonesian portion of the island of Borneo, known for its vast rainforests, rich biodiversity, and significant natural resources.
  • B. Borneo
    Borneo is the world’s third-largest island in Southeast Asia, known for its vast rainforests, rich biodiversity, and division among Indonesia, Malaysia, and Brunei.
  • C. Borneo Island
    Borneo Island is a modern residential island in Amsterdam’s Eastern Docklands, known for its contemporary architecture and waterfront urban design.
  • D. Sundaland
    Sundaland is a biogeographical region of Southeast Asia comprising the Malay Peninsula and the western Indonesian islands, known for its high biodiversity and past exposure as a contiguous landmass during periods of low sea level.
  • E. Sumatra
    Sumatra is a large Indonesian island in western Indonesia known for its rich biodiversity, active volcanoes, and significant role in regional trade and history.
  • 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_69a889132b488190bbb43ad4780ddd92 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abc66d7ea081908867ff494b70df1e completed March 7, 2026, 6:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc01d9b40819089e6a59164e64949 completed March 10, 2026, 6:54 a.m.
Created at: March 4, 2026, 7:51 p.m.