Triple

T21550505
Position Surface form Disambiguated ID Type / Status
Subject Nicolas Léonard Sadi Carnot E531747 entity
Predicate givenName P17 FINISHED
Object Sadi 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: Sadi | Statement: [Nicolas Léonard Sadi Carnot, givenName, Sadi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sadi
Context triple: [Nicolas Léonard Sadi Carnot, givenName, Sadi]
  • A. Sadi chosen
    Sadi is the given name of Marie François Sadi Carnot, a 19th-century French statesman who served as President of France.
  • B. Abdul Salam
    Abdul Salam was an Iraqi military officer and politician who served as the President of Iraq from 1963 until his death in 1966.
  • C. Lotfi
    Lotfi is the given name of Lotfi A. Zadeh, the Azerbaijani-American computer scientist best known as the founder of fuzzy logic.
  • D. Al-Biruni
    Al-Biruni was an 11th-century Persian polymath renowned for his pioneering works in astronomy, mathematics, geography, and comparative religion.
  • E. Nassim
    Nassim is the first name of Nassim Nicholas Taleb, a Lebanese-American scholar, statistician, and former trader known for his work on risk, probability, and uncertainty.
  • 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_69e0c460232c81908de2c3819d17c00e completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb59258b88190966c18f1f519dad6 completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:28 p.m.