Triple
T38160414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zapfino Arabic |
E953000
|
entity |
| Predicate | supportsComplexShaping |
P190168
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Zapfino Arabic, supportsComplexShaping, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsComplexShaping Context triple: [Zapfino Arabic, supportsComplexShaping, yes]
-
A.
hasShapingType
Indicates a relationship where an entity is associated with the specific type or method by which it is formed, molded, or shaped.
-
B.
hasComplex
Indicates that one entity possesses, is associated with, or is part of a larger composite structure or complex formed with another entity.
-
C.
supportsRasterization
Indicates that one entity provides the capability or functionality for another entity to perform rasterization operations.
-
D.
usesOpenTypeFeatures
chosen
Indicates that one entity employs or supports OpenType typographic features in relation to another entity or context.
-
E.
supportsTiling
Indicates that one entity is capable of being arranged or repeated in a tiled pattern to cover a surface or domain without gaps or overlaps.
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037df1223c8190a5d61e4f8e6fd613 |
completed | May 12, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_6a037a1ad6c48190bfe35d350c1b4751 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:21 p.m.