Triple
T3253736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cleave |
E68246
|
entity |
| Predicate | hasSpellingType |
P457
|
FINISHED |
| Object | alternative spelling |
—
|
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: alternative spelling | Statement: [Cleave, hasSpellingType, alternative spelling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpellingType Context triple: [Cleave, hasSpellingType, alternative spelling]
-
A.
includesSpellType
Indicates that one entity (such as a spell list, spellbook, or ability) contains or covers a particular type or category of spell.
-
B.
hasVariantSpelling
chosen
Indicates that one term is an alternative spelling form of another term.
-
C.
hasPhonologicalType
Indicates that one entity is characterized by or classified as having a particular phonological type (e.g., in terms of sound structure or phonological category).
-
D.
hasLanguageType
Indicates that an entity is associated with a particular type or category of language (e.g., spoken, written, programming, sign).
-
E.
effectOnSpelling
Indicates a relationship where one factor influences or alters the way something is spelled.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf640fd8819083c3c0cc41db2ffc |
completed | March 8, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69ada41ae74081909a0d1d696be8e35e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.