Triple
T650933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rashi script |
E11343
|
entity |
| Predicate | requiresFontSupport |
P203
|
FINISHED |
| Object | specialized Hebrew fonts |
—
|
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: specialized Hebrew fonts | Statement: [Rashi script, requiresFontSupport, specialized Hebrew fonts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresFontSupport Context triple: [Rashi script, requiresFontSupport, specialized Hebrew fonts]
-
A.
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.
-
B.
supportsFeature
chosen
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
C.
hasGlyphRepertoireSize
Indicates the number of distinct glyphs included in an entity’s glyph repertoire.
-
D.
isSupportedBy
Indicates that an entity is upheld, sustained, or enabled by another entity, which provides necessary assistance, resources, or justification.
-
E.
hasSupported
Indicates that one entity has provided assistance, endorsement, or backing to another entity, either materially, emotionally, or through advocacy.
- 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f33b6d881908b6662b73d6fe833 |
completed | March 1, 2026, 8:19 p.m. |
| PD | Predicate disambiguation | batch_69a49d0eade081909c47e85ed55f808d |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.