Triple

T22917031
Position Surface form Disambiguated ID Type / Status
Subject Dana White E568759 entity
Predicate hasChild P369 FINISHED
Object Savannah White 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: Savannah White | Statement: [Dana White, hasChild, Savannah White]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Savannah White
Context triple: [Dana White, hasChild, Savannah White]
  • A. Savannah White chosen
    Savannah White is one of the children of UFC president Dana White and a member of his relatively private family.
  • B. Savannah Jackson
    Savannah Jackson is a successful, independent television producer navigating love, friendship, and self-discovery in Terry McMillan’s novel and its film adaptation "Waiting to Exhale."
  • C. Samaria Smith
    Samaria Smith is the daughter of American rapper and actor LL Cool J.
  • D. Cassandra Whitaker
    Cassandra Whitaker is a recurring character in the literary work "The Golden Apples," contributing to its interconnected narrative of small-town Southern life.
  • E. Savannah Curtis
    Savannah Curtis is a compassionate and idealistic young woman who becomes the love interest of soldier John Tyree in Nicholas Sparks' romantic drama "Dear John."
  • 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_69e2458d90c88190a58cead4e781ca6a completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1807a14648190b5d5f7d926f19320 completed April 29, 2026, 3:52 a.m.
Created at: April 17, 2026, 3:42 p.m.