Triple

T22795178
Position Surface form Disambiguated ID Type / Status
Subject Linda Larkin E564221 entity
Predicate voiceRole P12691 FINISHED
Object Princess Jasmine 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: Princess Jasmine | Statement: [Linda Larkin, voiceRole, Princess Jasmine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Princess Jasmine
Context triple: [Linda Larkin, voiceRole, Princess Jasmine]
  • A. Princess Jasmine chosen
    Princess Jasmine is the independent and strong-willed princess of Agrabah from Disney's animated film "Aladdin."
  • B. Princess Shams al-Nahar
    Princess Shams al-Nahar is a fictional royal heroine from the medieval Arabic tale "The Ebony Horse" in the One Thousand and One Nights collection, known for her beauty and central role in the story’s romantic adventure.
  • C. Princess Soraya
    Princess Soraya was the German-Iranian second wife of Mohammad Reza Shah Pahlavi, the last Shah of Iran, renowned for her beauty, tragic royal marriage, and later life as a European socialite and actress.
  • D. Princess Rym al-Ali
    Princess Rym al-Ali is a Jordanian royal and former journalist known for her work in media development and education, including founding the Jordan Media Institute.
  • E. Sheikha
    Sheikha is an honorific title used for female members of royal families or women of high social and political status in Arab and Islamic societies.
  • 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cd8e0c4819086da0488bea56a34 completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.