Triple

T13299607
Position Surface form Disambiguated ID Type / Status
Subject Joseph de Jussieu E316771 entity
Predicate studied P778 FINISHED
Object cinchona E970487 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: cinchona | Statement: [Joseph de Jussieu, studied, cinchona]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: cinchona
Context triple: [Joseph de Jussieu, studied, cinchona]
  • A. Cinchona chosen
    Cinchona is a genus of South American trees and shrubs best known as the natural source of quinine, a historic treatment for malaria.
  • B. Cinchona officinalis
    Cinchona officinalis is a South American tree historically significant as the original natural source of quinine, a key treatment for malaria.
  • C. Quassia
    Quassia is a genus of tropical flowering plants known for their intensely bitter compounds, which are used in traditional medicine and as natural insecticides.
  • D. Quillaja
    Quillaja is a genus of flowering trees known for their saponin-rich bark, commonly used as a natural soap and foaming agent.
  • E. Senna
    Senna is a critically acclaimed 2010 documentary film that chronicles the life, career, and tragic death of legendary Brazilian Formula One driver Ayrton Senna.
  • 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_69d806b40ab4819094adf6c374f4811a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990a43ed88190a8dbbbd7d6d62dc4 completed April 11, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716dd0cd88190b0ae81b402fc31cf completed May 3, 2026, 9:35 a.m.
Created at: April 9, 2026, 9:28 p.m.