Triple

T1575470
Position Surface form Disambiguated ID Type / Status
Subject Celtic nations E33639 entity
Predicate hasLanguage P15 FINISHED
Object Manx E67867 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: Manx | Statement: [Celtic nations, hasLanguage, Manx]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manx
Context triple: [Celtic nations, hasLanguage, Manx]
  • A. Manx chosen
    Manx is a Celtic language of the Goidelic branch traditionally spoken on the Isle of Man.
  • B. Waternish
    Waternish is a rural peninsula on the Isle of Skye in Scotland, known for its coastal scenery, crofting communities, and historic sites.
  • C. North Frisian
    North Frisian is a minority West Germanic language spoken along the northwest coast of Germany and on the North Frisian Islands, known for its numerous dialects and close relation to other Frisian languages.
  • D. Guernésiais
    Guernésiais is a Norman language variety traditionally spoken on the Channel Island of Guernsey and its surrounding islets.
  • E. Cornish
    Cornish is a revived Southwestern Brittonic Celtic language historically spoken in Cornwall, England.
  • 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_69a885f27a4c8190a4622252cdf54c00 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908d2cffc819090f3d5cbebae3307 completed March 5, 2026, 4:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad402b44688190b02e6d146f009854 completed March 8, 2026, 9:23 a.m.
Created at: March 4, 2026, 7:27 p.m.