Triple
T35582103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amora |
E1028249
|
entity |
| Predicate | transmitsTraditionTo |
P139349
|
FINISHED |
| Object | Savoraim |
—
|
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: Savoraim | Statement: [Amora, transmitsTraditionTo, Savoraim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transmitsTraditionTo Context triple: [Amora, transmitsTraditionTo, Savoraim]
-
A.
mainTradition
Indicates that one entity represents the primary or dominant tradition associated with another entity.
-
B.
continuedTraditionOf
chosen
Indicates that one entity carries on, preserves, or perpetuates a tradition, practice, or custom that originated with another entity.
-
C.
heritageTransmission
Indicates the passing down of cultural, historical, or familial heritage from one entity or generation to another.
-
D.
usesTradition
Indicates that one entity employs or draws upon a tradition as a guiding method, resource, or influence in its actions or practices.
-
E.
broadcastTradition
Indicates the act of transmitting or disseminating a cultural, social, or customary practice to an audience through some medium.
- 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_69f76e0495a081909beced418558c0b4 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff5b233e9c8190adc06cca0758986b |
completed | May 9, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69ff5a5682108190a006b23c4fcdcc7c |
completed | May 9, 2026, 4:01 p.m. |
Created at: May 3, 2026, 4:04 p.m.