Triple

T224805
Position Surface form Disambiguated ID Type / Status
Subject Haiti E4291 entity
Predicate officialLanguage P236 FINISHED
Object French E13984 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: French | Statement: [Haiti, officialLanguage, French]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: French
Context triple: [Haiti, officialLanguage, French]
  • A. French chosen
    French is a Romance language that evolved from Latin and is now spoken worldwide as both a native and official language in many countries.
  • B. FR
    FR is the IATA airline designator used to identify Ryanair flights.
  • C. French American
    French Americans are U.S. residents or citizens of French ancestry, including both descendants of early French settlers and more recent immigrants from France.
  • D. Old French
    Old French was the medieval Romance language spoken in northern France and surrounding regions, which served as the linguistic ancestor of modern French and significantly influenced English after the Norman Conquest.
  • E. Walloon language
    Walloon language is a regional Romance language spoken primarily in southern Belgium, particularly in Wallonia, with its own distinct phonology and vocabulary separate from standard French.
  • 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_69a2573508588190b522c2476d91acfe completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c8c0b8881908016161568c0cbfb completed Feb. 28, 2026, 3:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69a35277532c8190ab2815c63a564e33 completed Feb. 28, 2026, 8:39 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.