Triple
T17590478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | El Beida |
E428432
|
entity |
| Predicate | currency |
P245
|
FINISHED |
| Object | Libyan dinar |
—
|
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: Libyan dinar | Statement: [El Beida, currency, Libyan dinar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Libyan dinar Context triple: [El Beida, currency, Libyan dinar]
-
A.
Libyan dinar
chosen
The Libyan dinar is the official monetary unit of Libya, used for everyday transactions and economic activities throughout the country.
-
B.
Libyan pound
The Libyan pound was the former national currency of Libya used during the monarchy period before being replaced by the Libyan dinar.
-
C.
Algerian dinar
The Algerian dinar is the official monetary unit of Algeria, issued and regulated by the Bank of Algeria.
-
D.
Tunisian dinar
The Tunisian dinar is the official monetary unit of Tunisia, subdivided into 1,000 millimes and used for all domestic financial transactions.
-
E.
Sudanese dinar
The Sudanese dinar was the former currency of Sudan, used mainly in the 1990s and early 2000s before being replaced by a reintroduced Sudanese pound.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469e6e3888190b73a5b6d7e8c0a55 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 5:51 a.m.