Triple
T112762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judeo-Arabic |
E2282
|
entity |
| Predicate | scriptVariant |
P4680
|
FINISHED |
| Object | square Hebrew script |
—
|
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: square Hebrew script | Statement: [Judeo-Arabic, scriptVariant, square Hebrew script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptVariant Context triple: [Judeo-Arabic, scriptVariant, square Hebrew script]
-
A.
scriptType
Indicates the classification or category of a script, specifying what kind of script it is (e.g., its format, purpose, or scripting language type).
-
B.
script
Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
-
C.
scriptDirection
Indicates the direction in which a writing system or script is read or written (e.g., left-to-right, right-to-left, top-to-bottom).
-
D.
variant
chosen
Indicates that one entity is an alternative form, version, or variation of another entity.
-
E.
program
Indicates that an entity creates, writes, or develops a computer program or software application.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a258808ff08190a06b6206f635612b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a256425a488190959d71e39e699d90 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.