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.