Triple

T2190704
Position Surface form Disambiguated ID Type / Status
Subject Darzalex E49853 entity
Predicate targets P860 FINISHED
Object CD38
CD38 is a cell surface glycoprotein with ectoenzyme and receptor functions, highly expressed on plasma cells and targeted in therapies for multiple myeloma and other hematologic malignancies.
 E241387 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: CD38 | Statement: [Darzalex, targets, CD38]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CD38
Context triple: [Darzalex, targets, CD38]
  • A. Lextran
    Lextran is the public bus transit system serving Lexington and surrounding areas in Fayette County, Kentucky.
  • B. C-3a
    C-3a is a commuter rail line within the Cercanías Madrid network serving suburban areas around Spain’s capital.
  • C. DPPA
    DPPA is the United Nations department responsible for conflict prevention, peacemaking, and supporting political and peacebuilding efforts worldwide.
  • D. CASP13
    CASP13 is the 13th Critical Assessment of protein Structure Prediction experiment, an international community-wide competition that benchmarks computational methods for predicting 3D protein structures.
  • E. FACS
    FACS is a professional designation indicating a surgeon is a Fellow of the American College of Surgeons and meets its standards of education, training, and ethical practice.
  • 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: CD38
Triple: [Darzalex, targets, CD38]
Generated description
CD38 is a cell surface glycoprotein with ectoenzyme and receptor functions, highly expressed on plasma cells and targeted in therapies for multiple myeloma and other hematologic malignancies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CD38
Target entity description: CD38 is a cell surface glycoprotein with ectoenzyme and receptor functions, highly expressed on plasma cells and targeted in therapies for multiple myeloma and other hematologic malignancies.
  • A. Lextran
    Lextran is the public bus transit system serving Lexington and surrounding areas in Fayette County, Kentucky.
  • B. C-3a
    C-3a is a commuter rail line within the Cercanías Madrid network serving suburban areas around Spain’s capital.
  • C. DPPA
    DPPA is the United Nations department responsible for conflict prevention, peacemaking, and supporting political and peacebuilding efforts worldwide.
  • D. CASP13
    CASP13 is the 13th Critical Assessment of protein Structure Prediction experiment, an international community-wide competition that benchmarks computational methods for predicting 3D protein structures.
  • E. FACS
    FACS is a professional designation indicating a surgeon is a Fellow of the American College of Surgeons and meets its standards of education, training, and ethical practice.
  • 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_69abbf3f5e008190beda3ce5d77209e0 completed March 7, 2026, 6:01 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.
Created at: March 4, 2026, 7:46 p.m.