Triple

T2138640
Position Surface form Disambiguated ID Type / Status
Subject Tecentriq E46710 entity
Predicate targets P860 FINISHED
Object PD-L1
PD-L1 is an immune checkpoint protein expressed on various cells, including some cancer cells, that binds PD-1 to suppress immune responses and enable tumor immune evasion.
 E46710 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: PD-L1 | Statement: [Tecentriq, targets, PD-L1]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PD-L1
Context triple: [Tecentriq, targets, PD-L1]
  • A. REGN-EB3
    REGN-EB3 is a monoclonal antibody cocktail developed by Regeneron to treat Ebola virus disease, shown to significantly reduce mortality in clinical trials.
  • B. Alimta
    Alimta is a chemotherapy drug (pemetrexed) primarily used to treat malignant pleural mesothelioma and non-small cell lung cancer.
  • C. Tecentriq
    Tecentriq is an immunotherapy cancer drug (atezolizumab) that targets the PD-L1 protein to help the immune system attack tumors in various cancers.
  • D. mAb114
    mAb114 is a monoclonal antibody therapy developed to treat Ebola virus disease, shown to significantly reduce mortality during recent Ebola outbreaks.
  • E. CA-MB
    CA-MB is the ISO 3166-2 subdivision code that uniquely identifies the Canadian province of Manitoba in international standards.
  • 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: PD-L1
Triple: [Tecentriq, targets, PD-L1]
Generated description
PD-L1 is an immune checkpoint protein expressed on various cells, including some cancer cells, that binds PD-1 to suppress immune responses and enable tumor immune evasion.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PD-L1
Target entity description: PD-L1 is an immune checkpoint protein expressed on various cells, including some cancer cells, that binds PD-1 to suppress immune responses and enable tumor immune evasion.
  • A. REGN-EB3
    REGN-EB3 is a monoclonal antibody cocktail developed by Regeneron to treat Ebola virus disease, shown to significantly reduce mortality in clinical trials.
  • B. Alimta
    Alimta is a chemotherapy drug (pemetrexed) primarily used to treat malignant pleural mesothelioma and non-small cell lung cancer.
  • C. Tecentriq chosen
    Tecentriq is an immunotherapy cancer drug (atezolizumab) that targets the PD-L1 protein to help the immune system attack tumors in various cancers.
  • D. mAb114
    mAb114 is a monoclonal antibody therapy developed to treat Ebola virus disease, shown to significantly reduce mortality during recent Ebola outbreaks.
  • E. CA-MB
    CA-MB is the ISO 3166-2 subdivision code that uniquely identifies the Canadian province of Manitoba in international standards.
  • 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_69a88a174ab48190a5db20c132e5dccf completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbe012aa481909ffa0a50e58efabb completed March 7, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae51b1290c8190a08850b428c99a6c completed March 9, 2026, 4:50 a.m.
NEDg Description generation batch_69ae55923b748190bf7a2df3ae94edc8 completed March 9, 2026, 5:07 a.m.
NED2 Entity disambiguation (via description) batch_69ae55fdc32c8190b6ecdc9b23d64cc5 completed March 9, 2026, 5:09 a.m.
Created at: March 4, 2026, 7:44 p.m.