Triple

T15728914
Position Surface form Disambiguated ID Type / Status
Subject Ken Berry E381289 entity
Predicate familyName P18 FINISHED
Object Berry E325598 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: Berry | Statement: [Ken Berry, familyName, Berry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berry
Context triple: [Ken Berry, familyName, Berry]
  • A. Berry
    Berry is a historic province in central France known for its rural landscapes, medieval heritage, and traditional French culture.
  • B. Berry
    Berry is a small historic town on the South Coast of New South Wales, Australia, known for its rural charm, heritage buildings, and popular weekend tourism.
  • C. Berry chosen
    Berry is a common English surname borne by numerous individuals across various fields, including sports, politics, and the arts.
  • D. Pear
    Pear is a sweet, bell-shaped fruit from the Pyrus genus, widely cultivated and eaten fresh, canned, or as juice around the world.
  • E. Blueberry
    Blueberry is a translucent light-blue color variant famously used on Apple’s early iMac G3 computers.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fb4cc0081909efe330339474017 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82faa5508190a28e2a224d4a4a06 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:46 a.m.