Triple
T6290729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iudaeorum |
E141008
|
entity |
| Predicate | inscriptionLanguageSet |
P39087
|
FINISHED |
| Object | Latin part of trilingual titulus |
—
|
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: Latin part of trilingual titulus | Statement: [Iudaeorum, inscriptionLanguageSet, Latin part of trilingual titulus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionLanguageSet Context triple: [Iudaeorum, inscriptionLanguageSet, Latin part of trilingual titulus]
-
A.
inscriptionLanguageAtSite
chosen
Indicates that a particular language is used in inscriptions found at a given site.
-
B.
writesLanguage
Indicates that an entity produces written content in a particular language.
-
C.
languageOfLetters
Indicates that one entity is the language in which the other entity’s letters or written correspondence are composed.
-
D.
signatureLanguage
Indicates the language in which a signature (e.g., on a document or agreement) is written or expressed.
-
E.
isScheduledLanguageOf
Indicates that a particular language is officially planned or designated to be used for a specific event, program, or context.
- 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_69c008cdf2ac8190bb640c94478fb4ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0641ca91481909d49b700cef93ffe |
completed | March 22, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69c060df0d8881908215575862ef6831 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:27 p.m.