Triple

T20557981
Position Surface form Disambiguated ID Type / Status
Subject Joko Widodo E504771 entity
Predicate name P16 FINISHED
Object Joko Widodo NE NERFINISHED

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: Joko Widodo | Statement: [Joko Widodo, name, Joko Widodo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joko Widodo
Context triple: [Joko Widodo, name, Joko Widodo]
  • A. Joko Widodo chosen
    Joko Widodo is the President of Indonesia, known for his populist leadership style and focus on infrastructure development and bureaucratic reform.
  • B. Susilo Bambang Yudhoyono
    Susilo Bambang Yudhoyono is an Indonesian politician and retired army general who served as the country’s sixth president from 2004 to 2014.
  • C. Tien Suharto
    Tien Suharto was the First Lady of Indonesia during President Suharto’s rule, known for her influential role in social and charitable activities and her prominence in the country’s political elite.
  • D. Gibran Rakabuming Raka
    Gibran Rakabuming Raka is an Indonesian politician and businessman, known as the eldest son of President Joko Widodo and as the mayor of Surakarta.
  • E. Nadiem Makarim
    Nadiem Makarim is an Indonesian entrepreneur and former Minister of Education, Culture, Research, and Technology, best known as the co-founder and former CEO of the super-app company Gojek.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a5df84088190848c7eb35564d8f9 completed April 20, 2026, 10:17 p.m.
Created at: April 16, 2026, 11:38 a.m.