Triple

T629951
Position Surface form Disambiguated ID Type / Status
Subject Celebes E15903 entity
Predicate modernName P1213 FINISHED
Object Sulawesi E15903 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: Sulawesi | Statement: [Celebes, modernName, Sulawesi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sulawesi
Context triple: [Celebes, modernName, Sulawesi]
  • A. North Sulawesi
    North Sulawesi is a province in the northern part of Indonesia’s Sulawesi Island, known for its rich marine biodiversity, volcanic landscapes, and diverse cultures.
  • B. Celebes chosen
    Celebes, now known as Sulawesi, is a large, uniquely shaped island in Indonesia renowned for its diverse cultures, mountainous landscapes, and rich marine biodiversity.
  • C. 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.
  • D. Riau Islands
    The Riau Islands are an Indonesian archipelago in the South China Sea known for their strategic location near Singapore and Malaysia, maritime trade routes, and growing tourism industry.
  • E. Kalimantan
    Kalimantan is the Indonesian portion of the island of Borneo, known for its vast rainforests, rich biodiversity, and significant natural resources.
  • 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_69a4935c131c8190a5378c6bf101e8cc completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49ec051bc8190b3e3f8651a367d77 completed March 1, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a57403c0208190b3ff497aade61b29 completed March 2, 2026, 11:26 a.m.
Created at: March 1, 2026, 7:35 p.m.