Triple

T33341876
Position Surface form Disambiguated ID Type / Status
Subject Franc Zone E853692 entity
Predicate historicallyPeggedTo P13429 FINISHED
Object French franc NE NERFINISHED

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: French franc | Statement: [Franc Zone, historicallyPeggedTo, French franc]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: historicallyPeggedTo
Context triple: [Franc Zone, historicallyPeggedTo, French franc]
  • A. historicalPeg chosen
    Indicates a relationship where one entity’s value, status, or definition was formerly fixed or tied to another entity in the past.
  • B. currencyPeg
    Indicates that one currency’s value is fixed or tightly linked to the value of another currency or a basket of currencies.
  • C. peggedToEuroSince
    Indicates that the value of one currency or financial instrument has been fixed or tightly linked to the euro starting from a specific point in time.
  • D. isPegged
    Indicates that one entity’s value, status, or behavior is fixed or tightly linked to that of another entity, typically so that changes in the reference entity directly determine changes in the pegged entity.
  • E. wasReserveCurrency
    Indicates that a currency functioned as a primary reserve asset held by other entities, typically central banks or governments, during a specified time period.
  • 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_69f3496a1a588190bad9cbe9221144e0 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69fff9b126b4819085a4cf8791d388d1 completed May 10, 2026, 3:21 a.m.
PD Predicate disambiguation batch_69fff8f913a881908d3b7e490d92631f completed May 10, 2026, 3:18 a.m.
Created at: May 1, 2026, 1:34 a.m.