Triple

T14432851
Position Surface form Disambiguated ID Type / Status
Subject New Georgia E357877 entity
Predicate hasLanguage P15 FINISHED
Object Ghanongga language E533111 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: Ghanongga language | Statement: [New Georgia, hasLanguage, Ghanongga language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghanongga language
Context triple: [New Georgia, hasLanguage, Ghanongga language]
  • A. Ghanongga language chosen
    The Ghanongga language is an Oceanic language spoken by indigenous communities on New Georgia Island in the Solomon Islands.
  • B. Gonja language
    The Gonja language is a Gur language spoken primarily by the Gonja people in northern Ghana.
  • C. Gahuku language
    Gahuku language is a Papuan language spoken by the Gahuku people in Papua New Guinea.
  • D. Ganguela language
    The Ganguela language is a Bantu language spoken by the Ganguela people of southwestern Africa, particularly in Angola.
  • E. Gathang language
    Gathang language is an Aboriginal Australian language traditionally spoken by the Worimi and neighboring peoples of the mid-north coast of New South Wales.
  • 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_69d8279402a88190821ffa39ae15bccf completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91471a648190adb7b283a6a85c3e completed April 14, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bd3e6c48190b4fc3794202a0c3f completed May 8, 2026, 3:43 a.m.
Created at: April 10, 2026, 1:18 a.m.