Triple

T3234786
Position Surface form Disambiguated ID Type / Status
Subject The Beverly Hilton E67826 entity
Predicate developer P73 FINISHED
Object Conrad Hilton E103546 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: Conrad Hilton | Statement: [The Beverly Hilton, developer, Conrad Hilton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conrad Hilton
Context triple: [The Beverly Hilton, developer, Conrad Hilton]
  • A. Conrad Hilton chosen
    Conrad Hilton was an American hotelier and businessman best known as the founder of Hilton Hotels.
  • B. H. R. Hyatt
    H. R. Hyatt was a film editor known for his work on early British cinema, including Alfred Hitchcock’s 1934 thriller "The Man Who Knew Too Much."
  • C. Hudson Leverett
    Hudson Leverett is a descendant of John Leverett, a prominent colonial-era governor of the Massachusetts Bay Colony.
  • D. Howard W. Johnson
    Howard W. Johnson was an engineer and computer scientist known for his influential work in high-speed digital design and signal integrity.
  • E. César Ritz
    César Ritz was a pioneering Swiss hotelier and entrepreneur renowned for revolutionizing luxury hospitality and lending his name to some of the world’s most prestigious hotels.
  • 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_69ad858d27348190abb61c280b4c86a9 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaede0bdc8190a466f11bf2c50836 completed March 8, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b277404f6c8190803cf67cc8423430 completed March 12, 2026, 8:20 a.m.
Created at: March 8, 2026, 3:08 p.m.