Triple
T7512923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnsone |
E177565
|
entity |
| Predicate | hasSpellingRelation |
P457
|
FINISHED |
| Object | variant spelling of Johnson |
—
|
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: variant spelling of Johnson | Statement: [Johnsone, hasSpellingRelation, variant spelling of Johnson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpellingRelation Context triple: [Johnsone, hasSpellingRelation, variant spelling of Johnson]
-
A.
hasVariantSpelling
chosen
Indicates that one term is an alternative spelling form of another term.
-
B.
sharesSpellingWith
Indicates that two entities have identical or substantially identical written forms (i.e., they are spelled the same way).
-
C.
semanticRelation
Indicates a general meaning-based connection between two entities, such as similarity, implication, or conceptual association.
-
D.
phonologyRelation
Indicates a relationship between linguistic elements based on their phonological properties, such as sound patterns, features, or structures.
-
E.
hasLexicalInfluenceOn
Indicates that one linguistic element (such as a word, phrase, or lexicon) has affected or shaped the form, usage, or meaning of another linguistic element.
- 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_69c69f276b108190af2cc790b6554544 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5d52b2c8190ba32b1575756fa7c |
completed | March 27, 2026, 9:25 p.m. |
| PD | Predicate disambiguation | batch_69c6f4d44e9481909813e073b194f6f4 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:45 p.m.