Triple

T1831214
Position Surface form Disambiguated ID Type / Status
Subject Black Loyalists E40764 entity
Predicate departedFrom P1521 FINISHED
Object Charleston E13422 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: Charleston | Statement: [Black Loyalists, departedFrom, Charleston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charleston
Context triple: [Black Loyalists, departedFrom, Charleston]
  • A. Charleston chosen
    Charleston is a historic port city in South Carolina known as a key center of colonial resistance to British rule, including major protests against imperial taxation.
  • B. Charleston
    Charleston was the original name of the city now known as Lorain, Ohio, a Great Lakes industrial community on the shores of Lake Erie.
  • C. Charlotte
    Charlotte is a royal figure bearing the traditional title of Princess Royal, historically associated with the eldest daughter of the British monarch.
  • D. Columbia, South Carolina
    Columbia, South Carolina is the capital and largest city of South Carolina, known for its role as a regional center of government, education, and culture.
  • E. Mount Pleasant, South Carolina
    Mount Pleasant is a rapidly growing suburban town in the Charleston metropolitan area of South Carolina, known for its coastal setting, historic sites, and residential communities.
  • 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_69a8864644bc8190b2358ab897194ac1 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb022aef48190975b6d12fc6681ad completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf45fcd08190a82a4057470eb3ee completed March 8, 2026, 8:42 p.m.
Created at: March 4, 2026, 7:32 p.m.