Triple
T28423221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenwa people |
E719997
|
entity |
| Predicate | mainReligionBranch |
P4668
|
FINISHED |
| Object | Islam |
—
|
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: Islam | Statement: [Shenwa people, mainReligionBranch, Islam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainReligionBranch Context triple: [Shenwa people, mainReligionBranch, Islam]
-
A.
religiousBranchOf
Indicates that one religion, denomination, or sect is a subdivision or offshoot of a larger parent religious tradition.
-
B.
religionDominantBranch
chosen
Indicates that one religious branch is the primary or most prevalent form of a broader religion within a given context or population.
-
C.
majorReligionCanBe
Indicates that an entity can have a particular major religion as one of its possible primary religious affiliations.
-
D.
officialReligion
Indicates that a particular religion is formally recognized and designated as the official or state religion of an entity (such as a country or region).
-
E.
otherMajorReligion
Indicates that an entity’s primary religious affiliation is a major religion other than the one currently in focus or being referenced.
- 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_69eff6f1c5088190bc24bfbf92f9c017 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 1:35 a.m.