Triple

T22356943
Position Surface form Disambiguated ID Type / Status
Subject NO E552677 entity
Predicate author P4 FINISHED
Object Carl Djerassi 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: Carl Djerassi | Statement: [NO, author, Carl Djerassi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carl Djerassi
Context triple: [NO, author, Carl Djerassi]
  • A. Carl Djerassi chosen
    Carl Djerassi was an Austrian-American chemist best known for his pioneering role in the development of the first oral contraceptive pill.
  • B. Walter Ehrlich
    Walter Ehrlich is an individual notable enough to be recognized as a prominent bearer of the surname Ehrlich.
  • C. Tadeus Reichstein
    Tadeus Reichstein was a Polish-Swiss chemist and Nobel laureate renowned for his work on the synthesis of vitamin C and adrenal cortex hormones.
  • D. Hugo Ehrlich
    Hugo Ehrlich was a Croatian architect known for his significant contributions to early 20th-century architecture in Zagreb.
  • E. Albert Hofmann
    Albert Hofmann was a Swiss chemist best known for discovering the psychedelic properties of LSD and pioneering research into its effects on the human mind.
  • 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157d08b148190a9a4e445e8579219 completed April 29, 2026, 12:58 a.m.
Created at: April 16, 2026, 8:44 p.m.