Triple

T13338334
Position Surface form Disambiguated ID Type / Status
Subject Payment on Demand E317756 entity
Predicate starring P1507 FINISHED
Object Peggie Castle E518251 NE FINISHED

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: Peggie Castle | Statement: [Payment on Demand, starring, Peggie Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peggie Castle
Context triple: [Payment on Demand, starring, Peggie Castle]
  • A. Peggie Castle chosen
    Peggie Castle was an American film and television actress best known for her roles in 1950s Westerns and crime dramas, including a prominent part in the TV series "Lawman."
  • B. Orth Castle
    Orth Castle is a historic lakeside fortress located on an island in Austria’s Traunsee, renowned for its picturesque setting and cultural significance.
  • C. Penlyne Castle
    Penlyne Castle is a historic estate in the Blue Mountains of Jamaica, known for its scenic highland setting and colonial-era architecture.
  • D. Blaise Castle
    Blaise Castle is an 18th-century Gothic Revival sham castle and landmark located on the Blaise Castle estate in Bristol, England.
  • E. Tous Castle
    Tous Castle is a historic medieval fortress located in Sant Martí de Tous, in Catalonia, Spain.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d806b5a3c08190b42c267fb092f98a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99d01bf8481908cd3a99e5557b972 completed April 11, 2026, 12:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69f78acfd0e88190954533a7f282d83a completed May 3, 2026, 5:50 p.m.
Created at: April 9, 2026, 9:31 p.m.