Triple

T19904284
Position Surface form Disambiguated ID Type / Status
Subject James De Lancey E478370 entity
Predicate familyName P18 FINISHED
Object De Lancey NE NERFINISHED

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: De Lancey | Statement: [James De Lancey, familyName, De Lancey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: De Lancey
Context triple: [James De Lancey, familyName, De Lancey]
  • A. DeLancey chosen
    DeLancey is a surname historically associated with a prominent American family of Huguenot descent influential in colonial New York politics and society.
  • B. Renda St. Clair
    Renda St. Clair is an American businesswoman and rancher best known as the wife of former ExxonMobil CEO and U.S. Secretary of State Rex Tillerson.
  • C. Anthony St Leger
    Anthony St Leger was an 18th-century British army officer and politician best known for originating the classic English horse race that bears his name.
  • D. Conerly
    Conerly is a surname most notably associated with Charlie Conerly, a prominent mid-20th-century American football quarterback.
  • E. Clancey
    Clancey is a given name and surname, typically a variant spelling of Clancy, used for people and fictional characters.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65945cc2081908224902d5f042d7a completed April 20, 2026, 4:50 p.m.
Created at: April 10, 2026, 1:52 p.m.