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.