Triple

T8371876
Position Surface form Disambiguated ID Type / Status
Subject Scandoromani E197478 entity
Predicate hasLexifier P54158 FINISHED
Object Romani language E6220 NE FINISHED

How this triple was built (3 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: Romani language | Statement: [Scandoromani, hasLexifier, Romani language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romani language
Context triple: [Scandoromani, hasLexifier, Romani language]
  • A. Romani language chosen
    The Romani language is an Indo-Aryan language traditionally spoken by Romani communities across Europe and beyond, featuring numerous dialects influenced by the languages of the regions where its speakers live.
  • B. Romani
    The Romani are a traditionally nomadic ethnic group of Indian origin, now widely dispersed across Europe and beyond, known for their distinct language, culture, and history of marginalization.
  • C. Romanian language
    Romanian is a Romance language spoken primarily in Romania and Moldova, notable for preserving many features of Latin while incorporating significant Slavic and Balkan influences.
  • D. Vlach language
    The Vlach language is a group of Eastern Romance varieties spoken by Vlach communities in the Balkans and surrounding regions, closely related to Romanian.
  • E. Megleno-Romanian
    Megleno-Romanian is an Eastern Romance language variety spoken by a small ethnic community in the Meglen region, primarily in Greece and North Macedonia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasLexifier
Context triple: [Scandoromani, hasLexifier, Romani language]
  • A. usesLexifier chosen
    Indicates that one language or variety is formed using another language as its primary lexical source or base.
  • B. hasLinguisticElement
    Indicates that one entity includes, is associated with, or is characterized by a particular linguistic component such as a word, phrase, symbol, or other language element.
  • C. hasLexicalInfluenceOn
    Indicates that one linguistic element (such as a word, phrase, or lexicon) has affected or shaped the form, usage, or meaning of another linguistic element.
  • D. hasLinguisticFeature
    Indicates that an entity possesses a particular linguistic property, trait, or characteristic.
  • E. secondaryLexifier
    Indicates that one language serves as a secondary source of lexical items or vocabulary for another language, supplementing the primary lexifier.
  • F. None of above.

Provenance (4 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_69ca82f56730819080cec5d991c76f4c completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80a6944081909c4547688c9e70ae completed March 31, 2026, 8:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce02aab4488190abc63bace296e32a completed April 2, 2026, 5:46 a.m.
PD Predicate disambiguation batch_69cb70cd04b08190ab5f72afd22a7967 completed March 31, 2026, 6:59 a.m.
Created at: March 30, 2026, 6:01 p.m.