Triple
T27411928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karanga people |
E692175
|
entity |
| Predicate | sacredSiteAssociation |
P141680
|
FINISHED |
| Object | Matonjeni shrines |
—
|
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: Matonjeni shrines | Statement: [Karanga people, sacredSiteAssociation, Matonjeni shrines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sacredSiteAssociation Context triple: [Karanga people, sacredSiteAssociation, Matonjeni shrines]
-
A.
sacredHill
Indicates that a hill holds religious or spiritual significance within a belief system or tradition.
-
B.
shrineSignificance
Indicates the cultural, religious, or historical importance attributed to a particular shrine within its context.
-
C.
associatedShrineComplex
chosen
Indicates that one entity is linked or connected to a particular shrine complex, typically through location, function, or religious association.
-
D.
hasSpiritualSitesIn
Indicates that one entity possesses or contains spiritual or religious sites located within the boundaries of another entity.
-
E.
sacredTo
Indicates that one entity is regarded as holy, revered, or dedicated in honor of another entity, such as a deity, person, or concept.
- 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_69ef5205fc808190ad3efc5525b8e6d6 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62cdb62608190a8e1c84a631de5ce |
completed | May 2, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:32 p.m.