Triple

T4258030
Position Surface form Disambiguated ID Type / Status
Subject Kirsty Sword-Gusmão E96028 entity
Predicate language P15 FINISHED
Object Tetum E32226 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: Tetum | Statement: [Kirsty Sword-Gusmão, language, Tetum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tetum
Context triple: [Kirsty Sword-Gusmão, language, Tetum]
  • A. Tetum chosen
    Tetum is an Austronesian language and one of the official languages of Timor-Leste, widely used in government, education, and daily communication.
  • B. Tetun language
    The Tetun language is an Austronesian language spoken primarily in Timor-Leste, where it serves as one of the main national and official languages.
  • C. Madurese
    The Madurese are an Austronesian ethnic group from Madura Island and surrounding regions of Indonesia, known for their distinct language, Islamic traditions, and maritime and cattle-breeding culture.
  • D. Roviana language
    The Roviana language is an Oceanic language spoken primarily in the Western Province of the Solomon Islands, especially around Roviana Lagoon, and serves as an important regional lingua franca.
  • E. Sranan Tongo
    Sranan Tongo is an English- and Dutch-influenced creole language originating in Suriname, widely used as a lingua franca among its diverse ethnic communities.
  • 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_69b3454095ac81909c2494f7ff294af1 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34f7ec4508190a5067f1112ac7dca completed March 12, 2026, 11:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a88d3bf48190b26eb8ab848d320e completed March 14, 2026, 6:27 p.m.
Created at: March 12, 2026, 11:06 p.m.