Triple

T16032026
Position Surface form Disambiguated ID Type / Status
Subject Reggie E388868 entity
Predicate formalEquivalent P6530 FINISHED
Object Reginald E74967 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: Reginald | Statement: [Reggie, formalEquivalent, Reginald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Reginald
Context triple: [Reggie, formalEquivalent, Reginald]
  • A. Reginald chosen
    Reginald is a masculine given name of English origin that has been borne by various notable figures, including military officers, politicians, and artists.
  • B. Reginald Venable
    Reginald Venable was the husband of American stage and film actress Fay Bainter.
  • C. Reginald Wade
    Reginald Wade is a British civil engineer and military officer known for his role in building military roads in the Scottish Highlands in the early 18th century.
  • D. Reginald Little
    Reginald Little was one of the children of Louise Little, best known as the mother of civil rights leader Malcolm X.
  • E. Marvyn
    Marvyn is an English surname historically associated with families such as that of the Tudor-era politician James Marvyn.
  • 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: formalEquivalent
Context triple: [Reggie, formalEquivalent, Reginald]
  • A. formalizedUnder
    Indicates that something has been officially established, defined, or codified within the framework, authority, or provisions of a particular formal system, agreement, or institution.
  • B. equivalentIn
    Indicates that two entities are considered logically or functionally the same in meaning, status, or effect within a given context.
  • C. equivalentTo chosen
    Indicates that two entities represent the same concept, value, or state, and can be treated as interchangeable in the given context.
  • D. isFormalizedBy
    Indicates that something is given a defined, structured, or official form through a specific method, process, or representation.
  • E. formalismFor
    Indicates that one entity serves as a formal representation, framework, or notation specifically designed to model, describe, or reason about another entity.
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1ff63edb0819092cbb671967bbdcd completed April 17, 2026, 9:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbd1cafc81909125174eed475d55 completed May 10, 2026, 1:13 a.m.
PD Predicate disambiguation batch_69e1826f34c081908005bb736f1c485d completed April 17, 2026, 12:44 a.m.
Created at: April 10, 2026, 4:56 a.m.