Triple

T2370993
Position Surface form Disambiguated ID Type / Status
Subject Herceptin E46088 entity
Predicate hasBiosimilar P37220 FINISHED
Object trastuzumab-dkst
Trastuzumab-dkst is a biosimilar monoclonal antibody to trastuzumab used in the treatment of HER2-positive breast and gastric cancers.
 E46088 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: trastuzumab-dkst | Statement: [Herceptin, hasBiosimilar, trastuzumab-dkst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: trastuzumab-dkst
Context triple: [Herceptin, hasBiosimilar, trastuzumab-dkst]
  • A. Tecentriq
    Tecentriq is an immunotherapy cancer drug (atezolizumab) that targets the PD-L1 protein to help the immune system attack tumors in various cancers.
  • B. Herceptin
    Herceptin is a targeted monoclonal antibody drug used primarily to treat HER2-positive breast cancer by blocking the HER2 receptor on cancer cells.
  • C. Verzenio
    Verzenio is a prescription cancer medication (abemaciclib) used primarily to treat certain types of hormone receptor–positive, HER2-negative breast cancer.
  • D. Alimta
    Alimta is a chemotherapy drug (pemetrexed) primarily used to treat malignant pleural mesothelioma and non-small cell lung cancer.
  • E. Darzalex
    Darzalex is a monoclonal antibody drug (daratumumab) used primarily in the treatment of multiple myeloma.
  • 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: trastuzumab-dkst
Triple: [Herceptin, hasBiosimilar, trastuzumab-dkst]
Generated description
Trastuzumab-dkst is a biosimilar monoclonal antibody to trastuzumab used in the treatment of HER2-positive breast and gastric cancers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: trastuzumab-dkst
Target entity description: Trastuzumab-dkst is a biosimilar monoclonal antibody to trastuzumab used in the treatment of HER2-positive breast and gastric cancers.
  • A. Tecentriq
    Tecentriq is an immunotherapy cancer drug (atezolizumab) that targets the PD-L1 protein to help the immune system attack tumors in various cancers.
  • B. Herceptin chosen
    Herceptin is a targeted monoclonal antibody drug used primarily to treat HER2-positive breast cancer by blocking the HER2 receptor on cancer cells.
  • C. Verzenio
    Verzenio is a prescription cancer medication (abemaciclib) used primarily to treat certain types of hormone receptor–positive, HER2-negative breast cancer.
  • D. Alimta
    Alimta is a chemotherapy drug (pemetrexed) primarily used to treat malignant pleural mesothelioma and non-small cell lung cancer.
  • E. Darzalex
    Darzalex is a monoclonal antibody drug (daratumumab) used primarily in the treatment of multiple myeloma.
  • F. None of above.

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_69a88a145268819083e2736cb835c696 completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abc76f5aec8190867d621e6849258c completed March 7, 2026, 6:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69aea8a2b1448190b19179cf379993ee completed March 9, 2026, 11:01 a.m.
NEDg Description generation batch_69aeac6b13ac81909042dddef15ec924 completed March 9, 2026, 11:18 a.m.
NED2 Entity disambiguation (via description) batch_69aead16b0a881909103e26053cfad84 completed March 9, 2026, 11:20 a.m.
Created at: March 4, 2026, 7:56 p.m.