Triple

T10483813
Position Surface form Disambiguated ID Type / Status
Subject Martin Haspelmath E247239 entity
Predicate coEditorOf P8375 FINISHED
Object The World Atlas of Language Structures Online E865605 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: The World Atlas of Language Structures Online | Statement: [Martin Haspelmath, coEditorOf, The World Atlas of Language Structures Online]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The World Atlas of Language Structures Online
Context triple: [Martin Haspelmath, coEditorOf, The World Atlas of Language Structures Online]
  • A. World Atlas of Language Structures chosen
    The World Atlas of Language Structures is a large-scale, comparative database and reference work that maps structural features of languages around the world.
  • B. Loanwords in the World’s Languages
    "Loanwords in the World’s Languages" is a comprehensive linguistic reference work that surveys and analyzes how and why words are borrowed across a wide range of the world’s languages.
  • C. UNESCO Atlas of the World’s Languages in Danger
    The UNESCO Atlas of the World’s Languages in Danger is an online reference work that documents and maps endangered languages worldwide, providing information on their vitality and risk of extinction.
  • D. Glottolog
    Glottolog is a comprehensive bibliographic and classification database of the world’s languages and dialects, maintained by linguists at the Max Planck Institute.
  • E. Foundations of Language
    Foundations of Language is a major theoretical work by linguist Ray Jackendoff that proposes an integrated, cognitive-science-based account of how linguistic structure relates to meaning, perception, and the mind.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509678ac88190984f18a2162e2dcf completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d933c5caa08190a5fba92ebf4b0ff9 completed April 10, 2026, 5:30 p.m.
Created at: April 6, 2026, 12:22 p.m.