Triple

T3291360
Position Surface form Disambiguated ID Type / Status
Subject Fatou Bensouda E69107 entity
Predicate succeededBy P78 FINISHED
Object Karim Ahmad Khan E65129 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: Karim Ahmad Khan | Statement: [Fatou Bensouda, succeededBy, Karim Ahmad Khan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karim Ahmad Khan
Context triple: [Fatou Bensouda, succeededBy, Karim Ahmad Khan]
  • A. Karim Ahmad Khan chosen
    Karim Ahmad Khan is a British barrister and international lawyer who serves as the Chief Prosecutor of the International Criminal Court, known for his work in international criminal and humanitarian law.
  • B. Omar Khan
    Omar Khan was a prominent 19th-century ruler of the Kokand Khanate in Central Asia, known for his patronage of culture and literature.
  • C. Khader Khan
    Khader Khan is a powerful and charismatic Mumbai mafia don and philosophical mentor figure in Gregory David Roberts’ novel *Shantaram*.
  • D. Mohammad Nasih
    Mohammad Nasih is an Indonesian academic who serves as the rector of Airlangga University, one of the country’s leading public universities.
  • E. Iskander Ali Mirza
    Iskander Ali Mirza was the first President of Pakistan, serving from 1956 until he was deposed in a military coup in 1958.
  • 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_69ad859d45748190b0742408c954b39f completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb05d0c908190a927d1af78e27de0 completed March 8, 2026, 5:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b35458a1248190b11e6756dfc318b7 completed March 13, 2026, 12:03 a.m.
Created at: March 8, 2026, 3:10 p.m.