Triple

T718302
Position Surface form Disambiguated ID Type / Status
Subject Melinda French Gates E14358 entity
Predicate familyName P18 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: [Melinda French Gates, familyName, French]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: French
Context triple: [Melinda French Gates, familyName, 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. The French
    The French is a renowned fine-dining restaurant in Manchester’s Midland Hotel, known for its modern British cuisine and historic, elegant setting.
  • E. 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.
  • 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_69a4934a36e081909e7abef98b898a4e completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a577658881909c12951d63d96377 completed March 1, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5dcb77bc481909d79542001fafbd2 completed March 2, 2026, 6:53 p.m.
Created at: March 1, 2026, 7:37 p.m.