Triple
T5565316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | אֵלִיָּהוּ |
E145865
|
entity |
| Predicate | זיכרון |
P15970
|
FINISHED |
| Object | שיר "אליהו הנביא" במוצאי שבת |
—
|
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: שיר "אליהו הנביא" במוצאי שבת | Statement: [אֵלִיָּהוּ, זיכרון, שיר "אליהו הנביא" במוצאי שבת]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: זיכרון Context triple: [אֵלִיָּהוּ, זיכרון, שיר "אליהו הנביא" במוצאי שבת]
-
A.
memory
chosen
Indicates that an entity retains, recalls, or is associated with stored information or past experiences.
-
B.
recall
Indicates that an entity retrieves or brings back into awareness information, events, or items that were previously known, experienced, or stored.
-
C.
memorizedBy
Indicates that some content, information, or material has been learned and retained in memory by a particular entity.
-
D.
rememberedFor
Indicates that one entity is known or recognized primarily because of, or in association with, another entity or achievement.
-
E.
recalledBy
Indicates that an entity is brought back, retrieved, or remembered as a result of another entity’s action or prompting.
- 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_69c008fdae24819081aa002ad99cd966 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c02033cc308190895f13454c57f452 |
completed | March 22, 2026, 5 p.m. |
| PD | Predicate disambiguation | batch_69c01b12826c8190969a584d0f53aa44 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:36 p.m.