Triple

T8504706
Position Surface form Disambiguated ID Type / Status
Subject 1921 Tulsa Race Massacre E201303 entity
Predicate recommendations P58814 FINISHED
Object reparations for survivors and descendants 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: reparations for survivors and descendants | Statement: [1921 Tulsa Race Massacre, recommendations, reparations for survivors and descendants]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: recommendations
Context triple: [1921 Tulsa Race Massacre, recommendations, reparations for survivors and descendants]
  • A. recommendation
    Indicates that one entity suggests, endorses, or advises another entity as suitable or beneficial for a particular purpose or context.
  • B. recommendationProcess
    Indicates the process by which one entity evaluates options and suggests a preferred choice or course of action to another entity.
  • C. recommendedIn chosen
    Indicates that one entity is suggested or endorsed within the context, content, or scope of another entity (such as a document, list, or recommendation source).
  • D. canRecommend
    Indicates that one entity is able or authorized to suggest or endorse another entity as suitable or preferable.
  • E. promotionPlaces
    Indicates that one entity designates or assigns another entity to a higher position, rank, or status within some organizational or hierarchical structure.
  • F. None of above.

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_69ca831fe47c8190b5c57b456d2aefa0 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5d8b7208190b199c56bf366c692 completed March 31, 2026, 3:18 p.m.
PD Predicate disambiguation batch_69cbd10cfd208190a519049fad32c508 completed March 31, 2026, 1:50 p.m.
Created at: March 30, 2026, 6:14 p.m.