Triple

T23741328
Position Surface form Disambiguated ID Type / Status
Subject Jarawan Bantu languages E586679 entity
Predicate areRelevantTo P37 FINISHED
Object reconstruction of Bantu language history 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: reconstruction of Bantu language history | Statement: [Jarawan Bantu languages, areRelevantTo, reconstruction of Bantu language history]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: areRelevantTo
Context triple: [Jarawan Bantu languages, areRelevantTo, reconstruction of Bantu language history]
  • A. relevantToInstitution
    Indicates that something has a meaningful connection, applicability, or significance to a particular institution.
  • B. relatedTo chosen
    Indicates a general, non-specific relationship or association exists between two entities.
  • C. hasLegalRelevanceIn
    Indicates that something is legally significant, applicable, or has consequences within a specified legal context, case, or jurisdiction.
  • D. mayRelateTo
    Indicates a possible, but not certain, relationship or association between two entities.
  • E. moreCloselyRelatedTo
    Indicates that one entity has a stronger or closer relationship, connection, or similarity to a second entity than to some other reference entity.
  • 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_69e24908efb08190bf755c3a9b91f222 completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1bad61d908190a0a8493bbba95d49 completed April 29, 2026, 8:01 a.m.
PD Predicate disambiguation batch_69f155f012808190a4b1cbc155558ade completed April 29, 2026, 12:50 a.m.
Created at: April 17, 2026, 7:11 p.m.