Triple

T23650347
Position Surface form Disambiguated ID Type / Status
Subject Gleevec E584150 entity
Predicate targetsProtein P153037 FINISHED
Object BCR-ABL
BCR-ABL is an abnormal fusion tyrosine kinase produced by the Philadelphia chromosome translocation, driving the development of chronic myeloid leukemia and some acute lymphoblastic leukemias.
 E1596292 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: BCR-ABL | Statement: [Gleevec, targetsProtein, BCR-ABL]
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: BCR-ABL
Triple: [Gleevec, targetsProtein, BCR-ABL]
Generated description
BCR-ABL is an abnormal fusion tyrosine kinase produced by the Philadelphia chromosome translocation, driving the development of chronic myeloid leukemia and some acute lymphoblastic leukemias.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: targetsProtein
Context triple: [Gleevec, targetsProtein, BCR-ABL]
  • A. targetsReceptor
    Indicates that one entity is directed toward, binds to, or is designed to act upon a specific receptor.
  • B. targetsGene
    Indicates that one entity is directed toward, acts upon, or is intended to affect a specific gene.
  • C. targetsProvision
    Indicates that one entity is the intended recipient or beneficiary of a provision, service, or resource supplied by another entity.
  • D. targetsDiseaseVector
    Indicates that an entity is directed at, designed to affect, or intended to control a particular disease-carrying vector organism.
  • E. isTherapeuticTargetIn
    Indicates that a biological entity (e.g., gene, protein, pathway) is used or proposed as a therapeutic target within a specified disease, condition, or treatment context.
  • 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_69e248fefafc81909656921192f30e80 completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1b2885b408190a43dfed93309a4d6 completed April 29, 2026, 7:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f45acbcec8190982a4a6f0b859331 completed May 21, 2026, 5:49 p.m.
NEDg Description generation batch_6a0f47336054819084117d5f59c7b7df completed May 21, 2026, 5:56 p.m.
NED2 Entity disambiguation (via description) batch_6a0f48696d40819093e5fbeffa0b8925 completed May 21, 2026, 6:01 p.m.
PD Predicate disambiguation batch_69f118d7903c8190bb590a71771e93af completed April 28, 2026, 8:30 p.m.
PDg Predicate description generation batch_69f1233300bc8190ac1639bdca1d7d99 completed April 28, 2026, 9:14 p.m.
Created at: April 17, 2026, 6:49 p.m.