Triple

T19992604
Position Surface form Disambiguated ID Type / Status
Subject APOE gene E494100 entity
Predicate encodesProtein P90097 FINISHED
Object apolipoprotein E precursor NE NERFINISHED

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: apolipoprotein E precursor | Statement: [APOE gene, encodesProtein, apolipoprotein E precursor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: apolipoprotein E precursor
Context triple: [APOE gene, encodesProtein, apolipoprotein E precursor]
  • A. LDL receptor
    The LDL receptor is a cell-surface protein that binds and internalizes low-density lipoprotein particles, playing a central role in cholesterol homeostasis and cardiovascular disease risk.
  • B. APOE ε2
    APOE ε2 is a common apolipoprotein E gene variant associated with a reduced risk of late-onset Alzheimer’s disease but an increased risk of type III hyperlipoproteinemia.
  • C. APOE gene
    The APOE gene encodes apolipoprotein E, a key protein in lipid metabolism whose variants, especially ε4, strongly influence risk for Alzheimer’s disease and cardiovascular disorders.
  • D. NPC1L1 transporter
    The NPC1L1 transporter is an intestinal membrane protein that mediates cholesterol absorption from the gut and is inhibited by the lipid-lowering drug ezetimibe.
  • E. APOE ε3 allele
    The APOE ε3 allele is the most common and generally considered the “neutral” variant of the apolipoprotein E gene, associated with average risk for Alzheimer’s disease and typical lipid metabolism compared to other APOE alleles.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: apolipoprotein E precursor
Target entity description: Apolipoprotein E precursor is a lipid-transport protein that, after processing to apolipoprotein E, plays a key role in cholesterol metabolism and is strongly implicated in cardiovascular and neurodegenerative diseases, including Alzheimer’s disease.
  • A. LDL receptor
    The LDL receptor is a cell-surface protein that binds and internalizes low-density lipoprotein particles, playing a central role in cholesterol homeostasis and cardiovascular disease risk.
  • B. APOE ε2
    APOE ε2 is a common apolipoprotein E gene variant associated with a reduced risk of late-onset Alzheimer’s disease but an increased risk of type III hyperlipoproteinemia.
  • C. APOE gene chosen
    The APOE gene encodes apolipoprotein E, a key protein in lipid metabolism whose variants, especially ε4, strongly influence risk for Alzheimer’s disease and cardiovascular disorders.
  • D. NPC1L1 transporter
    The NPC1L1 transporter is an intestinal membrane protein that mediates cholesterol absorption from the gut and is inhibited by the lipid-lowering drug ezetimibe.
  • E. APOE ε3 allele
    The APOE ε3 allele is the most common and generally considered the “neutral” variant of the apolipoprotein E gene, associated with average risk for Alzheimer’s disease and typical lipid metabolism compared to other APOE alleles.
  • F. None of above.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: encodesProtein
Context triple: [APOE gene, encodesProtein, apolipoprotein E precursor]
  • A. encodes
    Indicates that one entity contains or represents the information, instructions, or structure of another in a coded or symbolic form.
  • B. encodedByGene chosen
    Indicates that a particular gene is responsible for producing or specifying the sequence of a given molecule (such as a protein or RNA).
  • C. isProtein
    Indicates that the subject entity is classified as a protein.
  • D. typicalProtein
    Indicates that one entity is a representative or characteristic example of a particular protein type or class.
  • E. proteinContent
    Indicates the amount or proportion of protein present in a given entity or substance.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65fe10ffc81908c94168b0a8ea9c9 completed April 20, 2026, 5:18 p.m.
PD Predicate disambiguation batch_69e537fd311881908448f2aea8b4812e completed April 19, 2026, 8:15 p.m.
Created at: April 11, 2026, 3:31 p.m.