Triple
T6757551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katakana |
E154499
|
entity |
| Predicate | hasHalfwidthForms |
P73320
|
FINISHED |
| Object | Halfwidth Katakana |
—
|
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: Halfwidth Katakana | Statement: [Katakana, hasHalfwidthForms, Halfwidth Katakana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHalfwidthForms Context triple: [Katakana, hasHalfwidthForms, Halfwidth Katakana]
-
A.
hasFullForm
Indicates that one entity is the complete, expanded, or unabbreviated form of another entity.
-
B.
hasTraditionalCharacter
Indicates that an entity is associated with or represented by a traditional (non-simplified or historically established) written character form.
-
C.
hasLigatures
Indicates that one writing system, font, or text includes combined character forms (ligatures) that join two or more individual glyphs into a single symbol.
-
D.
hasUnicode
Indicates that an entity is associated with, represented by, or encoded using a specific Unicode character or sequence.
-
E.
hasContextualLetterForms
Indicates that the written form of a letter changes shape depending on its surrounding characters or position within a word.
- F. None of above. chosen
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_69c6880fd5808190be684854081e27dd |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d327e37081909d576e6eff9eec97 |
completed | March 27, 2026, 6:57 p.m. |
| PD | Predicate disambiguation | batch_69c6d09227108190b253b91967831a85 |
completed | March 27, 2026, 6:46 p.m. |
| PDg | Predicate description generation | batch_69c6d3264b7481908816a4d19543fb7b |
completed | March 27, 2026, 6:57 p.m. |
Created at: March 27, 2026, 2:11 p.m.