Triple

T11343888
Position Surface form Disambiguated ID Type / Status
Subject Don Draper E268668 entity
Predicate seriesFinaleScene P38927 FINISHED
Object meditating at a California retreat LITERAL 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: meditating at a California retreat | Statement: [Don Draper, seriesFinaleScene, meditating at a California retreat]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: seriesFinaleScene
Context triple: [Don Draper, seriesFinaleScene, meditating at a California retreat]
  • A. seriesFinaleOf
    Indicates that one work is the concluding or last installment of a particular series.
  • B. laterFinale
    Indicates that one event, episode, or occurrence serves as a concluding part that happens after another referenced event or finale.
  • C. finalSceneAction chosen
    Indicates the action or event that occurs in the concluding or final scene of a narrative or sequence.
  • D. seriesRunEnd
    Indicates the point or event at which a series, sequence, or recurring run of something concludes.
  • E. isFinalChapterOf
    Indicates that one entity is the concluding or last chapter within the sequence of chapters of another entity (typically a work or volume).
  • F. None of above.

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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d80148e2048190a716b515d78efdd1 completed April 9, 2026, 7:43 p.m.
PD Predicate disambiguation batch_69d7e6f8aeb4819080476f16a69b2ee3 completed April 9, 2026, 5:50 p.m.
Created at: April 8, 2026, 9:33 p.m.