Triple
T36598652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Addai (pseudonymous authorship) |
E902864
|
entity |
| Predicate | languageOfAssociatedText |
P129014
|
FINISHED |
| Object | Syriac |
—
|
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: Syriac | Statement: [Addai (pseudonymous authorship), languageOfAssociatedText, Syriac]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfAssociatedText Context triple: [Addai (pseudonymous authorship), languageOfAssociatedText, Syriac]
-
A.
languageOfKeyText
Indicates that a specified language is the primary language in which a given key or central text is written.
-
B.
languageText
chosen
Indicates that a piece of text is expressed in, or associated with, a particular language.
-
C.
contentLanguage
Indicates the language in which the content is expressed or intended to be understood.
-
D.
languageOfTranslations
Indicates that one entity is the language into which another entity (such as a text or work) has been translated.
-
E.
associatedLanguageScript
Indicates that there is a relationship between a language and the script or writing system used to represent it.
- 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_69f76e66b7b88190848f7a3e1188915f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a013a251b4081908b43d85dd95586c5 |
completed | May 11, 2026, 2:08 a.m. |
| PD | Predicate disambiguation | batch_6a0137e4ea988190812173a5ff044098 |
completed | May 11, 2026, 1:59 a.m. |
Created at: May 3, 2026, 4:11 p.m.