Triple

T7321586
Position Surface form Disambiguated ID Type / Status
Subject Roger Adams E168559 entity
Predicate notableStudent P4838 FINISHED
Object Carl Djerassi E130681 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: Carl Djerassi | Statement: [Roger Adams, notableStudent, Carl Djerassi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carl Djerassi
Context triple: [Roger Adams, notableStudent, 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. Eugene G. Rochow
    Eugene G. Rochow was an American inorganic chemist renowned for pioneering organosilicon chemistry and the direct process for producing silicones, achievements that earned him the Priestley Medal.
  • 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_69c68a5251508190ad68df4151cfeb04 completed March 27, 2026, 1:46 p.m.
NER Named-entity recognition batch_69c6ef1ba58481909cfb5030b85f385a completed March 27, 2026, 8:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7ef01ea8c819091cd4106039c121e completed March 28, 2026, 3:08 p.m.
Created at: March 27, 2026, 3:03 p.m.