Triple

T9744237
Position Surface form Disambiguated ID Type / Status
Subject Sarah P. Duke E236264 entity
Predicate memberOf P10 FINISHED
Object Duke family E272410 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: Duke family | Statement: [Sarah P. Duke, memberOf, Duke family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke family
Context triple: [Sarah P. Duke, memberOf, Duke family]
  • A. Duke family chosen
    The Duke family is a prominent American family known for its vast tobacco and energy fortune and for its major philanthropic contributions, including the endowment of Duke University.
  • B. Bruce family
    The Bruce family was a powerful medieval Scottish noble dynasty that produced several prominent figures, including Robert the Bruce, King of Scots.
  • C. Hall family
    The Hall family is a familial group or lineage to which Sylvia Hall belongs.
  • D. Rose family
    The Rose family is a prominent benefactor family whose legacy and contributions are commemorated through institutions such as the Rose Museum.
  • E. Lee family
    The Lee family is a prominent American dynasty from Virginia, historically influential in politics and the military and best known for producing figures such as Confederate General Robert E. Lee.
  • 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_69ca84d3e24481908a476e2231123cf9 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f2e5bb081908047e3bf5fe3991c completed April 1, 2026, 10:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1affb761881908dde9a4f028c32f6 completed April 5, 2026, 12:42 a.m.
Created at: March 30, 2026, 8:23 p.m.