Triple

T16952526
Position Surface form Disambiguated ID Type / Status
Subject Daypro E411217 entity
Predicate hasPregnancyRisk P125370 FINISHED
Object avoid use in late pregnancy LITERAL 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: avoid use in late pregnancy | Statement: [Daypro, hasPregnancyRisk, avoid use in late pregnancy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasPregnancyRisk
Context triple: [Daypro, hasPregnancyRisk, avoid use in late pregnancy]
  • A. hasPregnancyCategory
    Indicates the classification of a drug or substance based on its known or potential risks when used during pregnancy.
  • B. hasStageOfPregnancy
    Indicates that an entity is in, or associated with, a specific stage or phase of pregnancy.
  • C. pregnantBy
    Indicates that one entity is carrying a pregnancy that was biologically conceived by another specified entity.
  • D. isPregnantIn
    Indicates that an entity is in a state of pregnancy during a specified time or within a particular context.
  • E. hasSurrogatePregnancyFor
    Indicates that one entity is carrying a pregnancy on behalf of another entity, typically with the intention of giving the resulting child to that other entity.
  • F. None of above. chosen

Provenance (4 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_69d886c9c9d481909afe222093641cae completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d0197f308190af7185fc9cc7a6e9 completed April 18, 2026, 6:40 p.m.
PD Predicate disambiguation batch_69e32b9aa8748190b248890aca86753d completed April 18, 2026, 6:58 a.m.
PDg Predicate description generation batch_69e355722040819098830dabf207ecd6 completed April 18, 2026, 9:57 a.m.
Created at: April 10, 2026, 5:31 a.m.