Triple
T10117652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irish minuscule |
E223202
|
entity |
| Predicate | hasGlyphType |
P42388
|
FINISHED |
| Object | distinctive insular letterforms |
—
|
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: distinctive insular letterforms | Statement: [Irish minuscule, hasGlyphType, distinctive insular letterforms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGlyphType Context triple: [Irish minuscule, hasGlyphType, distinctive insular letterforms]
-
A.
hasGlyphsFor
Indicates that one entity provides or contains the necessary glyphs or visual symbols to represent another entity.
-
B.
hasTypography
chosen
Indicates that one entity uses, is associated with, or is characterized by a particular typographic style, font, or text layout.
-
C.
hasGlyphRepertoireSize
Indicates the number of distinct glyphs included in an entity’s glyph repertoire.
-
D.
hasTypicalCharacterType
Indicates that an entity is commonly associated with or exemplified by a particular type of character or persona.
-
E.
hasColorType
Indicates that an entity is associated with a specific category or type of color.
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd26317948190901197adbac01ed3 |
completed | April 2, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:04 p.m.