Triple

T2190669
Position Surface form Disambiguated ID Type / Status
Subject Xarelto E49852 entity
Predicate isMetabolizedBy P37221 FINISHED
Object CYP2J2
CYP2J2 is a human cytochrome P450 enzyme primarily expressed in the heart and other tissues, involved in the metabolism of various drugs and endogenous fatty acids.
 E242413 NE FINISHED

How this triple was built (4 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: CYP2J2 | Statement: [Xarelto, isMetabolizedBy, CYP2J2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CYP2J2
Context triple: [Xarelto, isMetabolizedBy, CYP2J2]
  • A. BCRP
    BCRP is the Central Reserve Bank of Peru, the country’s monetary authority responsible for maintaining monetary stability and managing its currency and international reserves.
  • B. CYP
    CYP is the three-letter ISO 3166-1 alpha-3 country code assigned to Cyprus.
  • C. JES2
    JES2 (Job Entry Subsystem 2) is an IBM mainframe component that manages the input, scheduling, and output of batch jobs and print workloads in the z/OS operating system.
  • D. Corachol
    Corachol is a subfamily of Uto-Aztecan languages that includes closely related indigenous languages spoken in western Mexico.
  • E. Activase
    Activase is a brand-name form of the clot-dissolving drug alteplase, widely used as a thrombolytic treatment for acute ischemic stroke and certain types of heart attack and pulmonary embolism.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: CYP2J2
Triple: [Xarelto, isMetabolizedBy, CYP2J2]
Generated description
CYP2J2 is a human cytochrome P450 enzyme primarily expressed in the heart and other tissues, involved in the metabolism of various drugs and endogenous fatty acids.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CYP2J2
Target entity description: CYP2J2 is a human cytochrome P450 enzyme primarily expressed in the heart and other tissues, involved in the metabolism of various drugs and endogenous fatty acids.
  • A. BCRP
    BCRP is the Central Reserve Bank of Peru, the country’s monetary authority responsible for maintaining monetary stability and managing its currency and international reserves.
  • B. CYP
    CYP is the three-letter ISO 3166-1 alpha-3 country code assigned to Cyprus.
  • C. JES2
    JES2 (Job Entry Subsystem 2) is an IBM mainframe component that manages the input, scheduling, and output of batch jobs and print workloads in the z/OS operating system.
  • D. Corachol
    Corachol is a subfamily of Uto-Aztecan languages that includes closely related indigenous languages spoken in western Mexico.
  • E. Activase
    Activase is a brand-name form of the clot-dissolving drug alteplase, widely used as a thrombolytic treatment for acute ischemic stroke and certain types of heart attack and pulmonary embolism.
  • F. None of above. chosen

Provenance (5 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_69a88aaba3c48190b351cab9b26989ff completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc5b101d48190a321625720d537b6 completed March 7, 2026, 6:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5db0352c8190aa9c4c58460df3a4 completed March 9, 2026, 5:42 a.m.
NEDg Description generation batch_69ae5e5fe37c8190bcf73200d32f5faa completed March 9, 2026, 5:45 a.m.
NED2 Entity disambiguation (via description) batch_69ae5ed1e3208190b46d5e8361c2a5f6 completed March 9, 2026, 5:46 a.m.
Created at: March 4, 2026, 7:46 p.m.