Triple
T37945089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | לירה ישראלית |
E946583
|
entity |
| Predicate | הייתה המטבע הרשמי של |
P3071
|
FINISHED |
| Object | מדינת ישראל |
—
|
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: מדינת ישראל | Statement: [לירה ישראלית, הייתה המטבע הרשמי של, מדינת ישראל]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: הייתה המטבע הרשמי של Context triple: [לירה ישראלית, הייתה המטבע הרשמי של, מדינת ישראל]
-
A.
officialNameOfCurrency
Indicates the officially designated name of a particular currency used by an entity.
-
B.
representsOfficialCurrency
Indicates that one entity serves as the official legal tender or primary currency used within the jurisdiction or authority of another entity.
-
C.
formerCurrency
chosen
Indicates that an entity was once used as a currency in a place or time period but is no longer in official use.
-
D.
currencyOfOfficialEmblem
Indicates the currency that is depicted or symbolically represented on an official emblem.
-
E.
formerCurrencyManaged
Indicates that an entity previously had responsibility for managing or administering a particular currency, but no longer does so.
- 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_69f76ef531ac8190ae6d99e5786e76ec |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc7b78f9481909f4f8fc2e3fdcde1 |
completed | May 6, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69fbbd18c9908190928d274f8731dfa8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.