Triple

T994253
Position Surface form Disambiguated ID Type / Status
Subject House of Keys E21459 entity
Predicate electoralUnit P3462 FINISHED
Object single-seat constituencies 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: single-seat constituencies | Statement: [House of Keys, electoralUnit, single-seat constituencies]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: electoralUnit
Context triple: [House of Keys, electoralUnit, single-seat constituencies]
  • A. votingUnit chosen
    Indicates a relationship where an entity functions as a unit or body that casts votes or participates in a voting process.
  • B. electorate
    Indicates that an entity functions as the body of people entitled to vote in relation to a particular political unit, office, or decision.
  • C. electorateState
    Indicates the state or region in which a given electorate (voting district or constituency) is located or to which it belongs.
  • D. electorateCategory
    Indicates the classification of an electorate or voter group into a specific category based on defined electoral or demographic criteria.
  • E. apportionmentUnit
    Indicates a relationship where something (such as a resource, cost, or quantity) is divided or allocated according to a specified unit or basis of apportionment.
  • 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_69a493c476b48190b41fc5e793171cc6 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4c5e16881908cd5f7ba2fcd5084 completed March 1, 2026, 9:51 p.m.
PD Predicate disambiguation batch_69a4b2af071c819086c374a16307dfe0 completed March 1, 2026, 9:42 p.m.
Created at: March 1, 2026, 7:41 p.m.