Triple

T10847721
Position Surface form Disambiguated ID Type / Status
Subject Ban Hyun-hee E256057 entity
Predicate father P120 FINISHED
Object Ban Ki-moon E9341 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: Ban Ki-moon | Statement: [Ban Hyun-hee, father, Ban Ki-moon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ban Ki-moon
Context triple: [Ban Hyun-hee, father, Ban Ki-moon]
  • A. Ban Ki-moon chosen
    Ban Ki-moon is a South Korean diplomat who served as the eighth Secretary-General of the United Nations from 2007 to 2016.
  • B. Kofi Annan
    Kofi Annan was a Ghanaian diplomat who served as Secretary-General of the United Nations from 1997 to 2006 and was a co-recipient of the 2001 Nobel Peace Prize.
  • C. Gabriele Annan
    Gabriele Annan was a German-born British literary critic and editor known for her influential book reviews and contributions to major British publications.
  • D. John Annan
    John Annan is a notable individual who shares the surname associated with prominent figures such as former UN Secretary-General Kofi Annan.
  • E. Francisco Guterres
    Francisco Guterres is an East Timorese politician who served as President of Timor-Leste and is a prominent leader of the Fretilin party.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75113bc188190ac78df0c51d95de6 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69e344249f648190b541c7fad7a834f5 completed April 18, 2026, 8:43 a.m.
Created at: April 8, 2026, 9:20 p.m.