Triple

T30569103
Position Surface form Disambiguated ID Type / Status
Subject Sky Masterson E778071 entity
Predicate betInvolvingSarahBrown P27042 FINISHED
Object wager with Nathan Detroit about taking Sarah to Havana 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: wager with Nathan Detroit about taking Sarah to Havana | Statement: [Sky Masterson, betInvolvingSarahBrown, wager with Nathan Detroit about taking Sarah to Havana]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: betInvolvingSarahBrown
Context triple: [Sky Masterson, betInvolvingSarahBrown, wager with Nathan Detroit about taking Sarah to Havana]
  • A. outcomeForSarah
    Indicates the result, consequence, or effect that a given situation, action, or event has specifically for Sarah.
  • B. betting chosen
    Indicates engaging in a wager where one party risks something of value on the outcome of an uncertain event involving another entity.
  • C. mayHaveBringInBet
    Indicates that an entity is permitted to introduce or involve another entity in a bet or wagering arrangement.
  • D. gamblerInvolved
    Indicates that a gambler participates in, is affected by, or is otherwise directly involved in the specified event or situation.
  • E. hasOutsideBet
    Indicates that an entity has placed or holds a bet on an outcome considered an outside or less likely option in a given betting context.
  • 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_69f2249f8c148190ae7eb3912cde112a completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f68911752c8190bc42c92fce473f3c completed May 2, 2026, 11:30 p.m.
PD Predicate disambiguation batch_69f67e42d6688190b60e91d2c388c555 completed May 2, 2026, 10:44 p.m.
Created at: April 29, 2026, 8:21 p.m.