Triple

T2190670
Position Surface form Disambiguated ID Type / Status
Subject Xarelto E49852 entity
Predicate isSubstrateOf P37222 FINISHED
Object P-glycoprotein
P-glycoprotein is a membrane-bound efflux transporter protein that pumps various drugs and xenobiotics out of cells, influencing their absorption, distribution, and resistance profiles.
E241382 NE FINISHED

How this triple was built (5 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: P-glycoprotein | Statement: [Xarelto, isSubstrateOf, P-glycoprotein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: P-glycoprotein
Context triple: [Xarelto, isSubstrateOf, P-glycoprotein]
  • 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. Plegridy
    Plegridy is a pegylated interferon beta-1a medication used to treat relapsing forms of multiple sclerosis.
  • C. CB1 receptor
    The CB1 receptor is a G protein–coupled cannabinoid receptor in the brain and nervous system that mediates most of the psychoactive effects of cannabis.
  • D. programmed death-ligand 1
    Programmed death-ligand 1 (PD-L1) is an immune checkpoint protein expressed on various cells that suppresses T-cell activity by engaging PD-1, enabling tumors to evade immune surveillance.
  • E. Lipinski
    Lipinski is a Polish-origin surname borne by various notable individuals in fields such as sports, music, and politics.
  • 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: P-glycoprotein
Triple: [Xarelto, isSubstrateOf, P-glycoprotein]
Generated description
P-glycoprotein is a membrane-bound efflux transporter protein that pumps various drugs and xenobiotics out of cells, influencing their absorption, distribution, and resistance profiles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: P-glycoprotein
Target entity description: P-glycoprotein is a membrane-bound efflux transporter protein that pumps various drugs and xenobiotics out of cells, influencing their absorption, distribution, and resistance profiles.
  • 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. Plegridy
    Plegridy is a pegylated interferon beta-1a medication used to treat relapsing forms of multiple sclerosis.
  • C. CB1 receptor
    The CB1 receptor is a G protein–coupled cannabinoid receptor in the brain and nervous system that mediates most of the psychoactive effects of cannabis.
  • D. programmed death-ligand 1
    Programmed death-ligand 1 (PD-L1) is an immune checkpoint protein expressed on various cells that suppresses T-cell activity by engaging PD-1, enabling tumors to evade immune surveillance.
  • E. Lipinski
    Lipinski is a Polish-origin surname borne by various notable individuals in fields such as sports, music, and politics.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isSubstrateOf
Context triple: [Xarelto, isSubstrateOf, P-glycoprotein]
  • A. hasSubstrateInfluenceOn
    Indicates that one substrate affects, modifies, or determines the behavior, activity, or properties of another entity or process.
  • B. subunitOf
    Indicates that one entity functions as a component or smaller part within the structure or organization of another, larger entity.
  • C. isBackboneOf
    Indicates that one entity forms the main supporting structure or central framework upon which another entity fundamentally depends.
  • D. hasPartIn
    Indicates that an entity participates in or plays a role within a larger event, process, or composite entity.
  • E. isSubnetworkOf
    Indicates that one network is a contained, subordinate, or component part of another, larger network.
  • 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_69a88aaba3c48190b351cab9b26989ff completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbf9e99f08190892d34485c8f2f25 completed March 7, 2026, 6:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5db0352c8190aa9c4c58460df3a4 completed March 9, 2026, 5:42 a.m.
NEDg Description generation batch_69ae5e60b45c819088bf18ae564f0d1a completed March 9, 2026, 5:45 a.m.
NED2 Entity disambiguation (via description) batch_69ae5ec4a35c8190bffc7a183497e764 completed March 9, 2026, 5:46 a.m.
PD Predicate disambiguation batch_69abbda32d1881909d1fd83a751fb21c completed March 7, 2026, 5:54 a.m.
PDg Predicate description generation batch_69abbf9c77fc8190a323bcaf644fb2c5 completed March 7, 2026, 6:03 a.m.
Created at: March 4, 2026, 7:46 p.m.