Triple

T1968407
Position Surface form Disambiguated ID Type / Status
Subject Committee against Torture E42740 entity
Predicate worksToPrevent P33311 FINISHED
Object torture 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: torture | Statement: [Committee against Torture, worksToPrevent, torture]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: worksToPrevent
Context triple: [Committee against Torture, worksToPrevent, torture]
  • A. worksTo
    Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
  • B. prevented
    Indicates that one entity stopped, hindered, or made it impossible for another entity or event to occur or proceed.
  • C. worksAs
    Indicates that an entity performs the role, job, or occupation specified by another entity.
  • D. worksThrough
    Indicates that one entity performs an action, causes an effect, or achieves a result by using, employing, or acting via another entity as an intermediary or means.
  • E. designedToAvoid
    Indicates that something was intentionally created or configured in a way that prevents or minimizes a particular outcome, condition, or interaction.
  • 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_69a88711151c8190940b2572095059d7 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb3d05cb88190963039d643bb6637 completed March 7, 2026, 5:12 a.m.
PD Predicate disambiguation batch_69abaff7d4a48190ab0d51aefb1c4e31 completed March 7, 2026, 4:56 a.m.
PDg Predicate description generation batch_69abb16a6db48190af04012e8ed2269f completed March 7, 2026, 5:02 a.m.
Created at: March 4, 2026, 7:36 p.m.