Triple

T12653780
Position Surface form Disambiguated ID Type / Status
Subject Vai language E302228 entity
Predicate hasHistoricalWritingDirection P2264 FINISHED
Object right-to-left (early Vai script usage) 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: right-to-left (early Vai script usage) | Statement: [Vai language, hasHistoricalWritingDirection, right-to-left (early Vai script usage)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasHistoricalWritingDirection
Context triple: [Vai language, hasHistoricalWritingDirection, right-to-left (early Vai script usage)]
  • A. hasWritingDirection chosen
    Indicates the direction in which writing or text is read or written for a given script, language, or text system.
  • B. hasHistoricalText
    Indicates that an entity is associated with a historical written document or record describing it or its past.
  • C. hasWritingHistory
    Indicates that an entity has a recorded history or log of its writing-related actions, changes, or authored content over time.
  • D. writingSystemHistorically
    Indicates that one writing system was historically used for, associated with, or served as a predecessor to another writing system.
  • E. hasWritingTraditionVia
    Indicates that an entity possesses or participates in a writing tradition by means of, or through the mediation of, another specified entity or method.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9617b07ec8190b714f04ae6654060 completed April 10, 2026, 8:45 p.m.
PD Predicate disambiguation batch_69d960b78ce8819091f15dd5013e6da5 completed April 10, 2026, 8:42 p.m.
Created at: April 9, 2026, 5:18 p.m.