Triple

T5196124
Position Surface form Disambiguated ID Type / Status
Subject John Clarke E117276 entity
Predicate familyName P18 FINISHED
Object Clarke E73353 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: Clarke | Statement: [John Clarke, familyName, Clarke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clarke
Context triple: [John Clarke, familyName, Clarke]
  • A. Clarke chosen
    Clarke is a common English and Irish surname historically associated with the occupation of a clerk or scholar.
  • B. Hadley
    Hadley is a given name most notably borne by Hadley Richardson, the first wife of writer Ernest Hemingway.
  • C. Tuthill
    Tuthill is a surname most notably associated with William Burnet Tuthill, the American architect who designed Carnegie Hall in New York City.
  • D. Risley
    Risley is a village in Derbyshire, England, known for its historic buildings and rural character near the town of Sandiacre.
  • E. Dunlap
    Dunlap is a residential neighborhood in Seattle’s Rainier Valley known for its diverse community and proximity to Lake Washington.
  • 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_69bd4462ed04819084fcb01eb9d2fa74 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a1c2184819083f4b1d8830bebae completed March 20, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee09a347081909c2c6c4a2362d7dd completed March 21, 2026, 6:16 p.m.
Created at: March 20, 2026, 1:46 p.m.