Triple

T21516636
Position Surface form Disambiguated ID Type / Status
Subject Saad Hariri E530859 entity
Predicate name P16 FINISHED
Object Saad Hariri 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: Saad Hariri | Statement: [Saad Hariri, name, Saad Hariri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saad Hariri
Context triple: [Saad Hariri, name, Saad Hariri]
  • A. Saad Hariri chosen
    Saad Hariri is a Lebanese politician and businessman who has served multiple terms as Prime Minister and is a leading Sunni figure in Lebanon’s post-civil war political landscape.
  • B. Rafic Hariri
    Rafic Hariri was a Lebanese businessman and politician who served multiple terms as Prime Minister and played a major role in the post-civil war reconstruction of Lebanon.
  • C. al-Hariri
    al-Hariri is the family name of Al-Hariri of Basra, a renowned medieval Arab poet and author celebrated for his maqamat (rhymed prose narratives).
  • D. Najib Mikati
    Najib Mikati is a Lebanese billionaire businessman and politician who has served multiple terms as Lebanon’s prime minister.
  • E. Maher Mikati
    Maher Mikati is a Lebanese businessman and member of the prominent Mikati family, known for their significant influence in politics and telecommunications.
  • 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_69e0c45d95a081908e7962ad215da746 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee814278e08190a66d516bed0726b5 completed April 26, 2026, 9:18 p.m.
Created at: April 16, 2026, 6:25 p.m.