Triple

T22453936
Position Surface form Disambiguated ID Type / Status
Subject Jane Rolfe E555062 entity
Predicate child P120 FINISHED
Object John Bolling 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: John Bolling | Statement: [Jane Rolfe, child, John Bolling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Bolling
Context triple: [Jane Rolfe, child, John Bolling]
  • A. Robert Bolling chosen
    Robert Bolling was a prominent 17th-century Virginia planter and politician, known as an early member of the colonial Bolling family that became influential in Southern aristocratic society.
  • B. Raynal C. Bolling
    Raynal C. Bolling was a pioneering U.S. Army Air Service officer and prominent corporate lawyer who helped organize American air power in World War I before being killed in action in France.
  • C. Phillip A. Talbert
    Phillip A. Talbert is a federal prosecutor who serves as the United States Attorney for the Eastern District of California.
  • D. William Mullen
    William Mullen is a personal name shared by multiple individuals, including figures in fields such as politics, sports, and academia.
  • E. David Ely
    David Ely was an American novelist and short story writer best known for his science fiction and speculative works, including the story that inspired the film "Seconds."
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4d6368819082cafbbd83339fbf completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.