Triple

T1604692
Position Surface form Disambiguated ID Type / Status
Subject Ga people E34474 entity
Predicate language P15 FINISHED
Object Ga language E155048 NE 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: Ga language | Statement: [Ga people, language, Ga language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ga language
Context triple: [Ga people, language, Ga language]
  • A. Ga language chosen
    The Ga language is a Niger-Congo language spoken primarily by the Ga people in and around Accra, the capital of Ghana.
  • B. Gane language
    The Gane language is an Austronesian language spoken by the Gane people in the southern part of Halmahera in eastern Indonesia.
  • C. Gbaya languages
    The Gbaya languages are a group of closely related Niger-Congo languages spoken primarily in the Central African Republic and neighboring regions by the Gbaya people.
  • D. Gedaged language
    Gedaged is an Austronesian language of the Western Oceanic branch spoken in coastal areas of Papua New Guinea.
  • E. Ha language
    Ha language is a Bantu language spoken primarily by the Ha people in western Tanzania, particularly around the shores of Lake Tanganyika.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a885fea6a481909fe83ba6441f1774 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9096a165c8190aec1d2ae6bd10e18 completed March 5, 2026, 4:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad51bcdebc81909520786c560598b6 completed March 8, 2026, 10:38 a.m.
Created at: March 4, 2026, 7:28 p.m.