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.