Triple

T23123115
Position Surface form Disambiguated ID Type / Status
Subject Graduate PLUS Loan E576952 entity
Predicate capitalizationPolicy P151002 FINISHED
Object unpaid interest may be capitalized 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: unpaid interest may be capitalized | Statement: [Graduate PLUS Loan, capitalizationPolicy, unpaid interest may be capitalized]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: capitalizationPolicy
Context triple: [Graduate PLUS Loan, capitalizationPolicy, unpaid interest may be capitalized]
  • A. capitalizationRequirement
    Indicates that a specified text element must follow a particular capitalization rule or standard.
  • 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. recognizesCapital
    Indicates that one entity acknowledges or identifies another entity as the capital of a given region or country.
  • E. capitalizedOn
    Indicates that one entity took advantage of, exploited, or made beneficial use of an opportunity, situation, or resource provided or created by 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_69e245f6c2e881909a228fdcfeb7c7d3 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e517a0481909829a73fdf255d1c completed April 29, 2026, 4:51 a.m.
PD Predicate disambiguation batch_69ef89f020588190b43393e048e7eda3 completed April 27, 2026, 4:08 p.m.
PDg Predicate description generation batch_69ef9b7494f4819088ae59ea3d0ae8ab completed April 27, 2026, 5:23 p.m.
Created at: April 17, 2026, 3:59 p.m.