Triple

T9807364
Position Surface form Disambiguated ID Type / Status
Subject programmed death-ligand 1 E238185 entity
Predicate expressedOn P90098 FINISHED
Object tumor cells LITERAL 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: tumor cells | Statement: [programmed death-ligand 1, expressedOn, tumor cells]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: expressedOn
Context triple: [programmed death-ligand 1, expressedOn, tumor cells]
  • A. expressesViewOn
    Indicates that one entity communicates or holds an opinion, stance, or perspective regarding another entity or topic.
  • B. endsOn
    Indicates that one entity terminates or concludes precisely at the boundary or endpoint of another entity.
  • C. definedOn
    Indicates that something (such as a function, rule, or structure) is specified to apply or be valid over a particular domain, set, or context.
  • D. reportedOn
    Indicates that one entity has provided an account, description, or coverage of another entity, typically as news, documentation, or an official report.
  • E. expressedThrough
    Indicates that something (such as an idea, emotion, or content) is conveyed, manifested, or communicated by means of a particular medium, form, or channel.
  • F. None of above. chosen

Provenance (4 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.
PD Predicate disambiguation batch_69cd03dd2da881909052fbf29736a773 completed April 1, 2026, 11:39 a.m.
PDg Predicate description generation batch_69cd06abc9248190a506b64e9c516d03 completed April 1, 2026, 11:51 a.m.
Created at: March 30, 2026, 8:29 p.m.