Triple

T9807401
Position Surface form Disambiguated ID Type / Status
Subject programmed death-ligand 1 E238185 entity
Predicate targetOfDrug P37016 FINISHED
Object durvalumab E505480 NE FINISHED

How this triple was built (2 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: durvalumab | Statement: [programmed death-ligand 1, targetOfDrug, durvalumab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: durvalumab
Context triple: [programmed death-ligand 1, targetOfDrug, durvalumab]
  • A. Libtayo
    Libtayo is a monoclonal antibody immunotherapy drug used primarily to treat certain types of advanced skin and lung cancers by targeting the PD-1 pathway.
  • B. Tecentriq
    Tecentriq is an immunotherapy cancer drug (atezolizumab) that targets the PD-L1 protein to help the immune system attack tumors in various cancers.
  • C. Keytruda
    Keytruda is a widely used immunotherapy cancer drug (pembrolizumab) that works by blocking the PD-1 pathway to help the immune system attack tumors.
  • D. Imfinzi chosen
    Imfinzi is a prescription immunotherapy drug (durvalumab) developed by AstraZeneca, primarily used to treat certain types of lung and bladder cancers by helping the immune system attack cancer cells.
  • E. Verzenio
    Verzenio is a prescription cancer medication (abemaciclib) used primarily to treat certain types of hormone receptor–positive, HER2-negative breast cancer.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca84defac48190abc1148804f184c1 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdab7ddaac8190a5584a5c863fbaa3 completed April 1, 2026, 11:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc57119881909616d835def02fc9 completed April 5, 2026, 2:43 a.m.
Created at: March 30, 2026, 8:29 p.m.