Triple

T2348753
Position Surface form Disambiguated ID Type / Status
Subject District of Columbia statehood referendum, 2016 E47394 entity
Predicate supportPercentage P38650 FINISHED
Object about 86 percent 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: about 86 percent | Statement: [District of Columbia statehood referendum, 2016, supportPercentage, about 86 percent]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: supportPercentage
Context triple: [District of Columbia statehood referendum, 2016, supportPercentage, about 86 percent]
  • A. support
    Indicates that one entity provides assistance, endorsement, or backing to another entity or its actions.
  • B. numberOfSupporters
    Indicates the quantity of entities that provide backing, endorsement, or support to a given entity or proposition.
  • C. supportsValue
    Indicates that one entity provides justification, evidence, or backing for the truth, relevance, or appropriateness of a particular value associated with another entity.
  • D. supportedSide
    Indicates that one entity backed, favored, or provided assistance to a particular side or party in a conflict, dispute, or competition.
  • E. supportedPopulation
    Indicates that one entity provides assistance, resources, or services to sustain or benefit a specified group of people.
  • 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_69a88a1b678c8190bce986922ba60ce0 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abcb802da08190980100444010f91e completed March 7, 2026, 6:53 a.m.
PD Predicate disambiguation batch_69abc5981ce48190a3f7852d28276e11 completed March 7, 2026, 6:28 a.m.
PDg Predicate description generation batch_69abcb7ebb708190ba7edffee3c45d8b completed March 7, 2026, 6:53 a.m.
Created at: March 4, 2026, 7:54 p.m.