Triple

T37348733
Position Surface form Disambiguated ID Type / Status
Subject Cionnaith E927256 entity
Predicate isNameRootOf P33904 FINISHED
Object McKenna NE NERFINISHED

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: McKenna | Statement: [Cionnaith, isNameRootOf, McKenna]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isNameRootOf
Context triple: [Cionnaith, isNameRootOf, McKenna]
  • A. isRootOf
    Indicates that one entity is the root or origin point from which another entity directly or indirectly descends or is derived.
  • B. isRootFormOf
    Indicates that one form of a word is the base or canonical form from which another inflected or derived form originates.
  • C. identifiesAsRoots
    Indicates that an entity is recognized or designated as the root or primary origin within a structure, hierarchy, or system.
  • D. rootName
    Indicates that the referenced node serves as the primary or top-level root in a hierarchical structure or dependency tree.
  • E. hasRootWord chosen
    Indicates that one linguistic form is derived from, based on, or directly associated with a specified root word.
  • F. None of above.

Provenance (3 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_69f76eb5e034819088e53ab5b7909a68 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fb8c38a9688190be524246f5682107 completed May 6, 2026, 6:45 p.m.
PD Predicate disambiguation batch_69fb5a9c6e0481908565bd849e869b24 completed May 6, 2026, 3:13 p.m.
Created at: May 3, 2026, 4:16 p.m.