Triple

T22473017
Position Surface form Disambiguated ID Type / Status
Subject Giuseppe Amato E555553 entity
Predicate notableWork P4 FINISHED
Object La romana 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: La romana | Statement: [Giuseppe Amato, notableWork, La romana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: La romana
Context triple: [Giuseppe Amato, notableWork, La romana]
  • A. Le Romain
    Le Romain is the nickname of Pierre Mignard, a prominent 17th-century French painter celebrated for his portraits and religious works.
  • B. The Roman Lady
    The Roman Lady is a painting by American Romantic artist Washington Allston, exemplifying his refined portrait style and interest in classical themes.
  • C. Woman of Rome chosen
    Woman of Rome is a 1954 Italian drama film starring Gina Lollobrigida as a young woman navigating love, hardship, and moral compromise in postwar Rome.
  • D. Romola
    Romola is a historical novel by George Eliot set in 15th-century Florence, exploring political upheaval, moral conflict, and personal transformation.
  • E. I sette re di Roma
    I sette re di Roma is an Italian theatrical and television work by Gigi Proietti that humorously revisits the legendary founding and early monarchs of ancient Rome.
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15be2034c81909d1263f2ed114b46 completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:49 p.m.