Triple
T37945113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | לירה ישראלית |
E946583
|
entity |
| Predicate | שימשה בתקופה |
P119523
|
FINISHED |
| Object | שנותיה הראשונות של מדינת ישראל |
—
|
LITERAL 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: שנותיה הראשונות של מדינת ישראל | Statement: [לירה ישראלית, שימשה בתקופה, שנותיה הראשונות של מדינת ישראל]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: שימשה בתקופה Context triple: [לירה ישראלית, שימשה בתקופה, שנותיה הראשונות של מדינת ישראל]
-
A.
תקופת חיבור
Indicates the time period during which the connection, composition, or formation of something took place.
-
B.
תקופה עלילתית
Indicates a narrative relationship where a specific time period serves as the setting or temporal framework for the plot or events of a story.
-
C.
usedDuringEraOf
chosen
Indicates that something was in use or actively employed during the time period or historical era associated with another entity.
-
D.
appearsInTimePeriod
Indicates that an entity is present, active, or occurs within a specified time period.
-
E.
תקופת חיים משוערת
Indicates an estimated or approximate time period during which the entity existed or was alive.
- 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.