Triple

T23263932
Position Surface form Disambiguated ID Type / Status
Subject Troy Donahue E582092 entity
Predicate notableWork P4 FINISHED
Object Rome Adventure 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: Rome Adventure | Statement: [Troy Donahue, notableWork, Rome Adventure]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rome Adventure
Context triple: [Troy Donahue, notableWork, Rome Adventure]
  • A. Rome Adventure chosen
    Rome Adventure is a 1962 romantic drama film set in Italy, starring Suzanne Pleshette as a young American woman who travels to Rome in search of love and self-discovery.
  • B. Gates of Rome
    The Gates of Rome are the historic monumental entrances in the Aurelian and earlier city walls that controlled access to ancient and medieval Rome along its major roads.
  • C. The Path to Rome
    The Path to Rome is a 1902 travelogue by Hilaire Belloc that blends pilgrimage, memoir, and social commentary as it recounts his walking journey across Europe to Rome.
  • D. Room in Rome
    Room in Rome is a 2010 Spanish erotic romantic drama film directed by Julio Medem that follows an intense, intimate night between two women in a Rome hotel room.
  • E. Rome Express
    Rome Express is a 1950 French crime thriller film featuring Maria Mauban in a prominent role.
  • 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_69e246079f58819085eaa9c260906880 completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f194cb76c48190869915cd93b44fcc completed April 29, 2026, 5:19 a.m.
Created at: April 17, 2026, 4:11 p.m.