Triple

T9972705
Position Surface form Disambiguated ID Type / Status
Subject FRONTIER Miles E196246 entity
Predicate rewardUnit P91380 FINISHED
Object miles balance 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: miles balance | Statement: [FRONTIER Miles, rewardUnit, miles balance]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: rewardUnit
Context triple: [FRONTIER Miles, rewardUnit, miles balance]
  • A. rewardSignal
    Indicates that one entity provides a signal representing feedback or incentive (such as a reward or penalty) to guide another entity’s behavior or learning process.
  • B. rewardModel
    Indicates a relationship where one entity serves as a model or framework for assigning rewards or evaluating outcomes for another entity or process.
  • C. rewardMechanism
    Indicates a relationship where an entity provides or defines a system of incentives or compensation in response to certain actions, behaviors, or outcomes.
  • D. monetaryReward
    Indicates that one entity provides or promises a payment of money to another as compensation, incentive, or prize.
  • E. rewardUse
    Indicates that one entity grants or provides a reward in response to the use or utilization of another entity.
  • F. None of above. chosen

Provenance (4 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_69ca82eea2b88190a0e511d21a31f386 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb7bb03688190a3f4fc1988b8fafa completed April 2, 2026, 12:26 a.m.
PD Predicate disambiguation batch_69cd1d9daa808190b413a1b9a1e929e2 completed April 1, 2026, 1:29 p.m.
PDg Predicate description generation batch_69cd358386f48190833c862b5b8c04b2 completed April 1, 2026, 3:10 p.m.
Created at: March 30, 2026, 8:48 p.m.