Triple
T28513322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | As Eyla |
E721548
|
entity |
| Predicate | governingCountryCurrency |
P78277
|
FINISHED |
| Object | Djiboutian 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: Djiboutian franc | Statement: [As Eyla, governingCountryCurrency, Djiboutian franc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governingCountryCurrency Context triple: [As Eyla, governingCountryCurrency, Djiboutian franc]
-
A.
currencyCountry
Indicates that a given currency is officially used as legal tender in a particular country.
-
B.
hostCountryCurrencyContext
Indicates the currency context or monetary environment associated with the host country in which an entity operates or a transaction occurs.
-
C.
currencyFamily
Indicates that two currencies belong to the same broader monetary family or classification, typically sharing a common origin, standard, or structural framework.
-
D.
localCurrency
chosen
Indicates that a particular currency is officially used or recognized as the standard medium of exchange within a specific locality, region, or country.
-
E.
currencySignAdopted
Indicates that a particular currency sign has been officially adopted for use with a given currency or monetary system.
- 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_69f01a5c072081908c7b04bcf6478da9 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fe831c97c88190b27ecf100e25c2a0 |
completed | May 9, 2026, 12:43 a.m. |
| PD | Predicate disambiguation | batch_69fe7f1b92648190b14e56bcaee5d0ca |
completed | May 9, 2026, 12:26 a.m. |
Created at: April 28, 2026, 3:14 a.m.