Triple

T20301101
Position Surface form Disambiguated ID Type / Status
Subject Imfinzi E505480 entity
Predicate targets P860 FINISHED
Object PD-L1 NE NERFINISHED

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: PD-L1 | Statement: [Imfinzi, targets, PD-L1]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PD-L1
Context triple: [Imfinzi, targets, PD-L1]
  • A. programmed death-ligand 1 chosen
    Programmed death-ligand 1 (PD-L1) is an immune checkpoint protein expressed on various cells that suppresses T-cell activity by engaging PD-1, enabling tumors to evade immune surveillance.
  • B. PD-1
    PD-1 is an inhibitory immune checkpoint receptor on T cells that downregulates immune responses and is a key target of cancer immunotherapy.
  • C. programmed cell death protein 1
    Programmed cell death protein 1 (PD-1) is an immune checkpoint receptor on T cells that downregulates immune responses and promotes self-tolerance, making it a key target in cancer immunotherapy.
  • D. nivolumab
    Nivolumab is a monoclonal antibody immunotherapy drug that blocks the PD-1 immune checkpoint to enhance the body’s anti-tumor response in various cancers.
  • E. HER2 receptor
    The HER2 receptor is a cell surface protein and member of the epidermal growth factor receptor family that, when overexpressed, drives the growth of certain aggressive breast and other cancers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6770c700c81909da247cef0d0f1eb completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:17 a.m.