Triple

T6383842
Position Surface form Disambiguated ID Type / Status
Subject Mohamed Nasheed E143650 entity
Predicate name P16 FINISHED
Object Mohamed Nasheed E143650 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: Mohamed Nasheed | Statement: [Mohamed Nasheed, name, Mohamed Nasheed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mohamed Nasheed
Context triple: [Mohamed Nasheed, name, Mohamed Nasheed]
  • A. Mohamed Nasheed chosen
    Mohamed Nasheed is a Maldivian politician and environmental advocate who served as President of the Maldives and became internationally known for his leadership on climate change and democracy.
  • B. Hassan Ali Khaire
    Hassan Ali Khaire is a Somali politician and former humanitarian and oil executive who served as the Prime Minister of Somalia from 2017 to 2020.
  • C. Hamdeen Sabahi
    Hamdeen Sabahi is an Egyptian leftist politician and Nasserist opposition figure who gained prominence as a leading candidate in the 2012 presidential election.
  • D. Sadiq al-Mahdi
    Sadiq al-Mahdi was a prominent Sudanese political leader and Islamic thinker who twice served as Prime Minister of Sudan and headed the National Umma Party.
  • E. Mazloum Abdi
    Mazloum Abdi is a prominent Kurdish military commander and key figure in the U.S.-backed campaign against ISIS in northeastern Syria.
  • 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_69c008dac1ec81909cef8157ccd69962 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06856434481909cbbca1c12c6e070 completed March 22, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69c638791ce8819081aeec3b11e1c96e completed March 27, 2026, 7:57 a.m.
Created at: March 22, 2026, 4:34 p.m.