Triple
T4012499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Idumaean |
E90677
|
entity |
| Predicate | laterLanguageShiftTo |
P4292
|
FINISHED |
| Object | Aramaic |
—
|
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: Aramaic | Statement: [Idumaean, laterLanguageShiftTo, Aramaic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterLanguageShiftTo Context triple: [Idumaean, laterLanguageShiftTo, Aramaic]
-
A.
languageShift
chosen
Indicates a change in the primary language used by an entity, such as switching from one language to another over time or in a given context.
-
B.
laterTranslatedAs
Indicates that something was translated at a later time into a different language, form, or version under a specified title or expression.
-
C.
languageShiftPressureFrom
Indicates pressure exerted by one entity that causes or encourages another entity to shift away from its current language toward a different language.
-
D.
languageBranch
Indicates that one language belongs to, or is classified under, a broader linguistic branch or subgroup.
-
E.
laterSyncretizedWith
Indicates that one element was subsequently merged or conflated with another into a single, combined form or identity.
- 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_69aed95e44088190aff7d90a151b1b20 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefaec08dc8190a341809059554f84 |
completed | March 9, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69aef8fa6fec81909b1190ecbba61410 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:34 p.m.