Triple
T3727563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashkenazi cursive Hebrew |
E81785
|
entity |
| Predicate | alphabetType |
P51274
|
FINISHED |
| Object | abjad |
—
|
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: abjad | Statement: [Ashkenazi cursive Hebrew, alphabetType, abjad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alphabetType Context triple: [Ashkenazi cursive Hebrew, alphabetType, abjad]
-
A.
alphabet
Indicates that one entity is an alphabet or set of symbols used for representing elements (such as characters or tokens) in relation to another entity.
-
B.
usesAlphabet
Indicates that one entity employs or is written using the alphabet or writing system associated with another entity.
-
C.
alphabetSizeLatin
Indicates the number of distinct letters in the Latin alphabet used in a given context or system.
-
D.
alphabeticCode
Indicates that one entity is identified or represented by a specific alphabetic code assigned to it.
-
E.
letterSequence
Indicates that one sequence of letters directly follows or is ordered in relation to another within a larger string or alphabetic arrangement.
- 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_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. |
| PDg | Predicate description generation | batch_69adc226fffc81909c679b44e611fee6 |
completed | March 8, 2026, 6:38 p.m. |
Created at: March 8, 2026, 3:34 p.m.