Triple
T3727564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashkenazi cursive Hebrew |
E81785
|
entity |
| Predicate | hasLetterFormsFor |
P9189
|
FINISHED |
| Object | 22 basic Hebrew consonants |
—
|
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: 22 basic Hebrew consonants | Statement: [Ashkenazi cursive Hebrew, hasLetterFormsFor, 22 basic Hebrew consonants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLetterFormsFor Context triple: [Ashkenazi cursive Hebrew, hasLetterFormsFor, 22 basic Hebrew consonants]
-
A.
hasDistinctLetterForms
Indicates that the related writing system or symbol set uses different visual shapes or styles for the same letter in different contexts (such as position, case, or usage).
-
B.
hasContextualLetterForms
chosen
Indicates that the written form of a letter changes shape depending on its surrounding characters or position within a word.
-
C.
hasThreeLetterForm
Indicates that an entity’s written or symbolic form consists of exactly three letters.
-
D.
hasLetterBy
Indicates that an entity possesses or is associated with a letter authored or sent by another entity.
-
E.
hasCyrillicAlphabetForm
Indicates that an entity has a corresponding representation or form written in the Cyrillic alphabet.
- 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_69ad8b1b7ef081908d2d381bbf54985a |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcaf7a6908190bd0c3bb5c55ab9ee |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc0452f5081909c79e114a86cce8c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.