Triple

T7528067
Position Surface form Disambiguated ID Type / Status
Subject Sam Rayburn E177946 entity
Predicate familyName P18 FINISHED
Object Rayburn E177946 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: Rayburn | Statement: [Sam Rayburn, familyName, Rayburn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rayburn
Context triple: [Sam Rayburn, familyName, Rayburn]
  • A. Rayburn chosen
    Rayburn is a surname most notably associated with Sam Rayburn, the long-serving Speaker of the United States House of Representatives.
  • B. Bill House
    Bill House was a pioneering mountaineer known for making the first ascent of Mount Waddington in the Coast Mountains of British Columbia.
  • C. Tydings Hall
    Tydings Hall is an academic building at the University of Maryland, College Park, housing social science departments and classrooms along the edge of McKeldin Mall.
  • D. Dirksen Senate Office Building
    The Dirksen Senate Office Building is one of the primary office buildings for members of the United States Senate, located just northeast of the U.S. Capitol in Washington, D.C.
  • E. Virginia Hill
    Virginia Hill was a notorious American mob courier and socialite closely linked to organized crime figures, most famously gangster Bugsy Siegel.
  • 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_69c69f29bf3081909a146aec7755f185 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f81cc5748190818443c48c9e3114 completed March 27, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84639c19881909e1736afc01a020d completed March 28, 2026, 9:20 p.m.
Created at: March 27, 2026, 3:47 p.m.