Triple

T33206194
Position Surface form Disambiguated ID Type / Status
Subject Terfenadine E850017 entity
Predicate affectsIonChannel P181366 FINISHED
Object hERG potassium channel
The hERG potassium channel is a cardiac ion channel crucial for repolarization of the heart’s electrical cycle and is a key target in drug-induced long QT syndrome and associated arrhythmias.
 E2041374 NE FINISHED

How this triple was built (3 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: hERG potassium channel | Statement: [Terfenadine, affectsIonChannel, hERG potassium channel]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: hERG potassium channel
Triple: [Terfenadine, affectsIonChannel, hERG potassium channel]
Generated description
The hERG potassium channel is a cardiac ion channel crucial for repolarization of the heart’s electrical cycle and is a key target in drug-induced long QT syndrome and associated arrhythmias.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: affectsIonChannel
Context triple: [Terfenadine, affectsIonChannel, hERG potassium channel]
  • A. affectsBehaviorOf
    Indicates that one entity produces a change or influence on the behavior, actions, or conduct of another entity.
  • B. affectsCellType
    Indicates that one entity produces an effect or change on a specific type of cell.
  • C. affectsChromosome
    Indicates a relationship where one entity produces a change or impact on the structure, function, or integrity of a chromosome.
  • D. affectsPhenomenon
    Indicates that one phenomenon produces an influence or change on another phenomenon.
  • E. affectsVariant
    Indicates that one entity has an influence or impact on a specific variant or version of another entity.
  • F. None of above. chosen

Provenance (7 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_69f3495fb92c819083ce65d0ddee7a76 completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69f7688dd3d08190ad13d0e780570a1c completed May 3, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a352fc6c310819094904da54c9e7a13 completed June 19, 2026, 12:02 p.m.
NEDg Description generation batch_6a35305f697c8190b02d778d33f27178 completed June 19, 2026, 12:04 p.m.
NED2 Entity disambiguation (via description) batch_6a353242c8148190910123613145e495 completed June 19, 2026, 12:12 p.m.
PD Predicate disambiguation batch_69f767fcf2f881908bacc7bfc38e68a5 completed May 3, 2026, 3:21 p.m.
PDg Predicate description generation batch_69f7688cea58819098bdfd7c80df7634 completed May 3, 2026, 3:23 p.m.
Created at: May 1, 2026, 1:30 a.m.