Triple

T23516012
Position Surface form Disambiguated ID Type / Status
Subject Thermopolis E574368 entity
Predicate usedBy P260 FINISHED
Object Mia Thermopolis 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: Mia Thermopolis | Statement: [Thermopolis, usedBy, Mia Thermopolis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mia Thermopolis
Context triple: [Thermopolis, usedBy, Mia Thermopolis]
  • A. Mia Thermopolis chosen
    Mia Thermopolis is the shy American teenager who discovers she is heir to the throne of the fictional European kingdom of Genovia in Meg Cabot’s The Princess Diaries series.
  • B. Nicolette
    Nicolette is a feminine given name, often associated with the English-language form of the French name Nicolette and borne by various notable figures in arts and entertainment.
  • C. Mia Ausa
    Mia Ausa is a young, kind-hearted magician and the daughter of the Magic Guild's leader in the role-playing game Lunar: The Silver Star.
  • D. Clementine Poidatz
    Clémentine Poidatz is a French actress known for her work in film and television, including roles in psychological thrillers and international productions.
  • E. Mia Serafino
    Mia Serafino is an American actress known for her work in film and television, including roles in independent movies and network sitcoms.
  • 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_69e245bb3dcc8190ba9a2b35972b58d0 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa81ab4c8190b85c8f80754020ea completed April 29, 2026, 6:51 a.m.
Created at: April 17, 2026, 6:08 p.m.