Triple
T11112995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mapam |
E262807
|
entity |
| Predicate | religionOrEthnicity |
P62585
|
FINISHED |
| Object | Jewish |
—
|
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: Jewish | Statement: [Mapam, religionOrEthnicity, Jewish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religionOrEthnicity Context triple: [Mapam, religionOrEthnicity, Jewish]
-
A.
ethnicOrReligiousGroup
chosen
Indicates that one entity is an ethnic or religious group to which the other entity belongs or with which it is associated.
-
B.
ethnicReligion
Indicates that a religion is closely associated with a particular ethnic group, often tied to that group’s culture, ancestry, or identity.
-
C.
religionMinority
Indicates that the subject’s religion is a minority faith within the relevant population or context.
-
D.
ethnicReligionMix
Indicates a relationship where a group or context involves a combined or overlapping presence of specific ethnic identities and religious affiliations.
-
E.
religionSignificantMinorityRegion
Indicates that a particular religion constitutes a significant minority presence within a specified geographic region.
- 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_69d6aa9b46cc8190b19f9f0cc45bf322 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79aa523588190a25d241ccc6a9679 |
completed | April 9, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69d7441cf8188190b8095f622c923156 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.