Triple
T35811915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | სომხები |
E1035253
|
entity |
| Predicate | ტრადიციული რელიგია |
P24121
|
FINISHED |
| Object | ქრისტიანობა |
—
|
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: ქრისტიანობა | Statement: [სომხები, ტრადიციული რელიგია, ქრისტიანობა]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ტრადიციული რელიგია Context triple: [სომხები, ტრადიციული რელიგია, ქრისტიანობა]
-
A.
traditionalReligionName
Indicates that an entity has a name specifically associated with a traditional or indigenous religion.
-
B.
religiousTraditions
chosen
Indicates a relationship where certain religious customs, practices, or belief systems are associated with or observed by an entity.
-
C.
religionAccordingToTradition
Indicates that an entity’s religion is identified or classified according to a particular tradition or customary understanding, rather than strictly formal or official criteria.
-
D.
previousReligiousTradition
Indicates that an entity had a different or prior religious affiliation or tradition before its current one.
-
E.
theologicalTradition
Indicates the religious or doctrinal school, lineage, or system of belief within which an entity’s theology is developed or practiced.
- 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d219f8819081dc4ce3c83ca0cb |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.