Triple

T1873732
Position Surface form Disambiguated ID Type / Status
Subject Fort William E39090 entity
Predicate languageUsed P238 FINISHED
Object Scottish Gaelic E367 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: Scottish Gaelic | Statement: [Fort William, languageUsed, Scottish Gaelic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scottish Gaelic
Context triple: [Fort William, languageUsed, Scottish Gaelic]
  • A. Scottish Gaelic chosen
    Scottish Gaelic is a Celtic language native to Scotland, historically spoken in the Highlands and Islands and closely related to Irish and Manx.
  • B. Scots
    Scots is a West Germanic language historically spoken in Lowland Scotland and parts of Ulster, closely related to English but with its own distinct vocabulary, grammar, and literary tradition.
  • C. Irish language
    The Irish language is a Goidelic Celtic language native to Ireland, known for its rich literary tradition and status as a national and first official language of the Republic of Ireland.
  • D. Goidelic
    Goidelic is the branch of Celtic languages that includes Irish, Scottish Gaelic, and Manx.
  • E. Waternish
    Waternish is a rural peninsula on the Isle of Skye in Scotland, known for its coastal scenery, crofting communities, and historic sites.
  • 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_69a8862f7074819096afe7fe65e179e9 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0d648ec8190a21445ddca6f9aa6 completed March 7, 2026, 5 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1de8728819090e80868f27c09af completed March 8, 2026, 7:45 p.m.
Created at: March 4, 2026, 7:34 p.m.