Triple

T25766830
Position Surface form Disambiguated ID Type / Status
Subject Teiwa language E648904 entity
Predicate hasMajorReferenceGrammar P75570 FINISHED
Object Teiwa (2010 grammar by Marian Klamer) 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: Teiwa (2010 grammar by Marian Klamer) | Statement: [Teiwa language, hasMajorReferenceGrammar, Teiwa (2010 grammar by Marian Klamer)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasMajorReferenceGrammar
Context triple: [Teiwa language, hasMajorReferenceGrammar, Teiwa (2010 grammar by Marian Klamer)]
  • A. hasReferenceGrammar chosen
    Indicates that an entity is associated with or described by a specific reference grammar resource.
  • B. hasReferenceGrammarBy
    Indicates that an entity is associated with or described by a reference grammar authored or compiled by a specified agent.
  • C. hasGrammar
    Indicates that an entity possesses, follows, or is associated with a particular system of grammatical rules or structure.
  • D. hasMajorLexifier
    Indicates that a language has another language as its primary lexical source or main contributor of its vocabulary.
  • E. hasGrammarFrom
    Indicates that one entity derives or uses its grammatical structure or rules from another 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_69e7ab322db0819092d6a2b3d4572e01 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f791cc969c8190bf187d6031a030d5 completed May 3, 2026, 6:19 p.m.
PD Predicate disambiguation batch_69f791033d288190b118029fe412b9c9 completed May 3, 2026, 6:16 p.m.
Created at: April 22, 2026, 5:11 a.m.