Triple

T3402749
Position Surface form Disambiguated ID Type / Status
Subject Umbundu E71693 entity
Predicate hasOrthographyBasedOn P9874 FINISHED
Object Portuguese-based Latin alphabet conventions 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: Portuguese-based Latin alphabet conventions | Statement: [Umbundu, hasOrthographyBasedOn, Portuguese-based Latin alphabet conventions]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasOrthographyBasedOn
Context triple: [Umbundu, hasOrthographyBasedOn, Portuguese-based Latin alphabet conventions]
  • A. hasOfficialOrthography
    Indicates that an entity has a formally recognized and standardized system for writing its language or name.
  • B. hasLanguageOfOrigin
    Indicates that one entity has its origin or source in the language specified by another entity.
  • C. hasStandardPronunciationBasedOn
    Indicates that one entity’s standard or canonical pronunciation is determined or derived from another entity’s pronunciation.
  • D. hasStandardOrthographySince
    Indicates that a language or writing system has used a particular standardized orthography starting from a specified point in time.
  • E. writingSystemDevelopedFrom chosen
    Indicates that one writing system originated, evolved, or was derived from another earlier writing system.
  • 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_69ad85aac4808190a092c9cc8911f584 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb8e78ec8819089417666dc29f412 completed March 8, 2026, 5:59 p.m.
PD Predicate disambiguation batch_69adadfa73ac8190a163f93e88d217f8 completed March 8, 2026, 5:12 p.m.
Created at: March 8, 2026, 3:14 p.m.