Triple

T14093138
Position Surface form Disambiguated ID Type / Status
Subject Holy Island E339184 entity
Predicate language P15 FINISHED
Object Welsh E61316 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: Welsh | Statement: [Holy Island, language, Welsh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Welsh
Context triple: [Holy Island, language, Welsh]
  • A. Welsh chosen
    Welsh is a Celtic language native to Wales, known for its rich literary tradition and status as one of the oldest living languages in Europe.
  • B. Italian Welsh
    Italian Welsh are people of Italian descent living in Wales, forming a distinct subgroup within the broader Italian community in the United Kingdom.
  • C. Old Welsh
    Old Welsh is the earliest documented stage of the Welsh language, attested in early medieval Britain and forming the linguistic ancestor of Middle and Modern Welsh.
  • D. Kernewek Kemmyn
    Kernewek Kemmyn is a standardized orthography of revived Cornish designed in the late 20th century to provide a more phonemic and consistent spelling system for the language.
  • 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_69d81c69b5c8819094aa1abf18302908 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5ee47f0881908aea8b5231b93f2f completed April 14, 2026, 3:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0aa2fbc8190b86fea2306363f1b completed May 7, 2026, 5:49 p.m.
Created at: April 9, 2026, 10:22 p.m.