Triple

T17898647
Position Surface form Disambiguated ID Type / Status
Subject Robert-Houdin E447500 entity
Predicate influenced P9 FINISHED
Object Harry Houdini 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: Harry Houdini | Statement: [Robert-Houdin, influenced, Harry Houdini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Houdini
Context triple: [Robert-Houdin, influenced, Harry Houdini]
  • A. Harry Houdini chosen
    Harry Houdini was a world-famous early 20th-century magician and escape artist renowned for his daring stunts, illusions, and feats of physical endurance.
  • B. Bess Houdini
    Bess Houdini was an American stage assistant and performer best known as the wife and professional partner of famed escape artist Harry Houdini.
  • C. Robert-Houdin
    Robert-Houdin was a 19th-century French magician and illusionist widely regarded as the father of modern conjuring.
  • D. Uri Geller
    Uri Geller is an Israeli-British illusionist and self-proclaimed psychic best known for his controversial spoon-bending feats and high-profile demonstrations of alleged paranormal abilities.
  • E. Dai Vernon
    Dai Vernon was a legendary Canadian magician and sleight-of-hand artist, often called "The Professor," who profoundly influenced modern close-up magic.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d81e00881908a46305af66fdf1a completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:19 a.m.