Triple

T14317224
Position Surface form Disambiguated ID Type / Status
Subject F.2d E354987 entity
Predicate citationStandard P24516 FINISHED
Object Bluebook E109776 NE FINISHED

How this triple was built (3 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: Bluebook | Statement: [F.2d, citationStandard, Bluebook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bluebook
Context triple: [F.2d, citationStandard, Bluebook]
  • A. Bluebook legal citation chosen
    Bluebook legal citation is the dominant standardized system in the United States for citing legal authorities and sources in legal writing and scholarship.
  • B. The Redbook: A Manual on Legal Style
    The Redbook: A Manual on Legal Style is a widely used reference guide that provides detailed rules and guidance for clear, precise, and consistent legal writing and citation.
  • C. AMA Manual of Style
    The AMA Manual of Style is a widely used guide that sets standards for writing, editing, and publishing in medical and scientific journals.
  • D. BCite
    BCite is a legal citation and research service that competes with KeyCite by providing tools to track the history, treatment, and validity of legal authorities.
  • E. The New York Times stylebook
    The New York Times stylebook is a widely used journalistic reference manual that sets detailed standards for grammar, usage, and formatting in news writing.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: citationStandard
Context triple: [F.2d, citationStandard, Bluebook]
  • A. citationStyle
    Indicates the specific formatting and referencing conventions used to cite sources in a document or publication.
  • B. citationType
    Indicates the specific kind or category of citation relationship that one entity has to another (e.g., reference, quotation, acknowledgment).
  • C. citationStyleName chosen
    Indicates the specific formatting style or standard used for creating citations or references.
  • D. citationAs
    Indicates that one entity is cited or referenced in the role or capacity specified by another entity (such as a particular work, version, or context).
  • E. citationFormatIncludes
    Indicates that a particular citation format specification contains or incorporates a given element, rule, or component as part of its structure.
  • F. None of above.

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_69d8278ed42c8190b9f882dcce611347 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8838e45c819080ee69dd39e3bd43 completed April 14, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd468a3b788190812ff0eed84fd139 completed May 8, 2026, 2:12 a.m.
PD Predicate disambiguation batch_69de2a9515f4819081aabf251bca5878 completed April 14, 2026, 11:52 a.m.
Created at: April 10, 2026, 1:12 a.m.