Triple

T25614497
Position Surface form Disambiguated ID Type / Status
Subject ANDA E642121 entity
Predicate NDAComparison P31276 FINISHED
Object relies on existing safety and efficacy data of reference drug 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: relies on existing safety and efficacy data of reference drug | Statement: [ANDA, NDAComparison, relies on existing safety and efficacy data of reference drug]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: NDAComparison
Context triple: [ANDA, NDAComparison, relies on existing safety and efficacy data of reference drug]
  • A. statusComparedToNPN
    Indicates how an entity’s status compares relative to a specified NPN (non-person name or reference) entity, such as being higher, lower, equal, or otherwise related in status.
  • B. comparisonType chosen
    Indicates the specific kind of comparison being made between two or more values or entities (e.g., equality, inequality, ordering, or similarity).
  • C. comparisonAspect
    Indicates that two or more entities are being compared specifically with respect to a particular shared attribute or dimension.
  • D. comparisonProperty
    Indicates that one entity is being compared to another based on a specific shared property or attribute.
  • E. comparisonReason
    Indicates that one entity is being compared to another specifically due to a stated reason, motive, or basis for the comparison.
  • F. None of above.

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_69e77e7a96748190b10f2699041e4e43 completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69f5f9e57720819080092db441fd60ef completed May 2, 2026, 1:19 p.m.
PD Predicate disambiguation batch_69f480789be08190ab252a6de3797200 completed May 1, 2026, 10:29 a.m.
Created at: April 21, 2026, 4:58 p.m.