Triple

T17413670
Position Surface form Disambiguated ID Type / Status
Subject East Sepik Province E423431 entity
Predicate hasLanguageFamily P1047 FINISHED
Object Sepik languages NE NERFINISHED

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: Sepik languages | Statement: [East Sepik Province, hasLanguageFamily, Sepik languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sepik languages
Context triple: [East Sepik Province, hasLanguageFamily, Sepik languages]
  • A. Yapen languages
    The Yapen languages are a group of closely related Austronesian languages spoken primarily on Yapen Island and nearby areas off the north coast of Western New Guinea in Indonesia.
  • B. Papuan languages
    Papuan languages are a diverse group of non-Austronesian language families spoken primarily on the island of New Guinea and neighboring regions, known for their great structural and genetic variety.
  • C. Baining languages
    Baining languages are a small group of Papuan languages spoken by the Baining people of eastern New Britain in Papua New Guinea.
  • D. Pama languages
    The Pama languages are a major subgroup of Australian Aboriginal languages spoken across northern Australia, forming part of the broader Pama–Nyungan language family.
  • E. Torres–Bismarck languages
    The Torres–Bismarck languages are a subgroup of Oceanic Austronesian languages spoken in the Torres Islands and Bismarck Archipelago region of the southwest Pacific.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sepik languages
Target entity description: The Sepik languages are a diverse family of Papuan languages spoken primarily along the Sepik River region of northern Papua New Guinea.
  • A. Yapen languages
    The Yapen languages are a group of closely related Austronesian languages spoken primarily on Yapen Island and nearby areas off the north coast of Western New Guinea in Indonesia.
  • B. Papuan languages chosen
    Papuan languages are a diverse group of non-Austronesian language families spoken primarily on the island of New Guinea and neighboring regions, known for their great structural and genetic variety.
  • C. Baining languages
    Baining languages are a small group of Papuan languages spoken by the Baining people of eastern New Britain in Papua New Guinea.
  • D. Pama languages
    The Pama languages are a major subgroup of Australian Aboriginal languages spoken across northern Australia, forming part of the broader Pama–Nyungan language family.
  • E. Torres–Bismarck languages
    The Torres–Bismarck languages are a subgroup of Oceanic Austronesian languages spoken in the Torres Islands and Bismarck Archipelago region of the southwest Pacific.
  • F. None of above.

Provenance (2 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44230fc688190a6a7edc12d9e9947 completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.