Triple
T31306655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabic Bayán |
E798349
|
entity |
| Predicate | scripturalLanguageFamily |
P142456
|
FINISHED |
| Object | Semitic languages |
—
|
NE NERFINISHED |
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: Semitic languages | Statement: [Arabic Bayán, scripturalLanguageFamily, Semitic languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scripturalLanguageFamily Context triple: [Arabic Bayán, scripturalLanguageFamily, Semitic languages]
-
A.
scripturalLanguageName
Indicates the name of the language in which a given scripture or sacred text is written.
-
B.
languageOfScripturalTradition
chosen
Indicates the language in which a given scriptural or religious textual tradition is expressed or transmitted.
-
C.
languageFamily
Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
-
D.
languageFamilyInCanon
Indicates that a language belongs to or is classified within a particular language family according to a specified canonical or authoritative source.
-
E.
titleLanguageFamily
Indicates the language family in which a given title is expressed or classified.
- 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_69f224e0bd4c8190aab9b29a73f7aa3c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7626667f48190ad90867eb67ec582 |
completed | May 3, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f76175d6608190b60b268e20f49ed9 |
completed | May 3, 2026, 2:53 p.m. |
Created at: April 29, 2026, 9:14 p.m.