Triple

T23513733
Position Surface form Disambiguated ID Type / Status
Subject Direct Unsubsidized Loan E572500 entity
Predicate capitalizationEffect P152668 FINISHED
Object increases total cost of the loan 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: increases total cost of the loan | Statement: [Direct Unsubsidized Loan, capitalizationEffect, increases total cost of the loan]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: capitalizationEffect
Context triple: [Direct Unsubsidized Loan, capitalizationEffect, increases total cost of the loan]
  • A. capitalizationPolicy
    Indicates the rules or conventions governing how letters are capitalized in a given context (e.g., text, names, or identifiers).
  • B. preferredCapitalization
    Indicates the specific way a term’s letters should be capitalized when it is written or displayed.
  • C. capitalizationSegment
    Indicates a relationship where a text span is treated as a distinct segment for applying or analyzing capitalization patterns.
  • D. isCapitalizationWeighted
    Indicates that something is evaluated or adjusted based on the relative capitalization (size or value of capital) of its components.
  • E. capitalizationRequirement
    Indicates that a specified text element must follow a particular capitalization rule or standard.
  • 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa80174c819088c9c19fdcf2a133 completed April 29, 2026, 6:51 a.m.
PD Predicate disambiguation batch_69f0621165c08190a0b27b1319733959 completed April 28, 2026, 7:30 a.m.
PDg Predicate description generation batch_69f0bd4a0e408190ad8916faf23562d9 completed April 28, 2026, 1:59 p.m.
Created at: April 17, 2026, 6:08 p.m.