Triple
T29054156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | קאוונא |
E735342
|
entity |
| Predicate | הייתה מרכז רבני חשוב עד |
P160973
|
FINISHED |
| Object | השואה |
—
|
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: השואה | Statement: [קאוונא, הייתה מרכז רבני חשוב עד, השואה]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: הייתה מרכז רבני חשוב עד Context triple: [קאוונא, הייתה מרכז רבני חשוב עד, השואה]
-
A.
كانت_مركزًا
chosen
Indicates that something served or functioned as a central point, hub, or focal place for something else.
-
B.
historicallyImportantCenter
Indicates that a place has served as a significant focal point of historical events, activities, or influence.
-
C.
tookPlaceAtReligiousCenter
Indicates that an event or action occurred at a religious center or place of worship.
-
D.
hasSynagogueHistory
Indicates that there exists a historical relationship or record connecting an entity to a synagogue, such as past ownership, use, events, or significance.
-
E.
עיר מרכזית קשורה
Indicates a relationship where one city is connected or associated with another city that serves as a central or main city in some defined context.
- 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6609061508190ae12005d993e42bc |
completed | May 2, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 10:10 a.m.