Triple

T15673236
Position Surface form Disambiguated ID Type / Status
Subject Paris (Orlando Bloom) E377371 entity
Predicate loveInterest P7325 FINISHED
Object Helen of Troy E24191 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: Helen of Troy | Statement: [Paris (Orlando Bloom), loveInterest, Helen of Troy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Helen of Troy
Context triple: [Paris (Orlando Bloom), loveInterest, Helen of Troy]
  • A. Helen of Troy chosen
    Helen of Troy is a legendary figure from Greek mythology renowned as the most beautiful woman in the world, whose abduction by Paris sparked the Trojan War.
  • B. Athénaïs
    Athénaïs was the familiar name of Madame de Montespan, the influential chief mistress of King Louis XIV of France and a prominent figure at the 17th-century French court.
  • C. Helen
    Helen is a fictional protagonist associated with a narrative set in or around New York City's Central Park.
  • D. Helen
    Helen is the given name of Maria Helen Van Schaack, likely used as her primary personal name.
  • E. Helen
    Helen is a central character in Ernest Hemingway’s short story “The Snows of Kilimanjaro,” portrayed as the wealthy, devoted wife and companion of the writer Harry during his final, reflective days in Africa.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2c996c8190a9ebe0e92608feaa completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff756b9af48190a634f23ace966ae9 completed May 9, 2026, 5:56 p.m.
Created at: April 10, 2026, 4:16 a.m.