Triple
T7159320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moroni |
E166897
|
entity |
| Predicate | currency |
P245
|
FINISHED |
| Object | Comorian franc |
E166900
|
NE 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: Comorian franc | Statement: [Moroni, currency, Comorian franc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Comorian franc Context triple: [Moroni, currency, Comorian franc]
-
A.
Comorian franc
chosen
The Comorian franc is the official monetary unit of the Union of the Comoros, issued by the Central Bank of the Comoros and pegged to the euro.
-
B.
Malagasy franc
The Malagasy franc was the former official currency of Madagascar used before the adoption of the ariary.
-
C.
French West African franc
The French West African franc was the colonial currency used across several territories in French West Africa before being replaced by the CFA franc.
-
D.
Mauritian dollar
The Mauritian dollar was a former currency of Mauritius that was eventually superseded by the Mauritian rupee.
-
E.
Guinean franc
The Guinean franc is the official national currency of Guinea, used for all monetary transactions within the country.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e811d6b081909dafeee1d820c74f |
completed | March 27, 2026, 8:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7adbbe8008190b470cf049ba4be52 |
completed | March 28, 2026, 10:30 a.m. |
Created at: March 27, 2026, 2:47 p.m.