Triple

T19564535
Position Surface form Disambiguated ID Type / Status
Subject Mary Palliser E489543 entity
Predicate familyName P18 FINISHED
Object Palliser 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: Palliser | Statement: [Mary Palliser, familyName, Palliser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Palliser
Context triple: [Mary Palliser, familyName, Palliser]
  • A. Palliser chosen
    Palliser is the aristocratic family name at the center of Anthony Trollope’s political and social novels, notably the Palliser series.
  • B. Sholto
    Sholto is a masculine given name of Scottish origin, historically associated with figures such as military leaders and nobles.
  • C. Kinnaird
    Kinnaird is a historic Scottish estate and locality traditionally associated with the Carnegie family and the title of Lord Carnegie of Kinnaird.
  • D. Mulgrave
    Mulgrave is a residential suburb in Melbourne, Victoria, Australia, known for its family-friendly streets, parks, and convenient access to major roads and shopping centres.
  • E. Mulgrave
    Mulgrave is an electoral district in the Queensland state parliament that includes the town of Gordonvale and surrounding areas.
  • 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63f76b220819096e668534c6bac67 completed April 20, 2026, 3 p.m.
Created at: April 10, 2026, 1:42 p.m.