Triple
T757090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dougga |
E15579
|
entity |
| Predicate | inscriptionLanguage |
P454
|
FINISHED |
| Object | Neo-Punic |
E30367
|
NE 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: Neo-Punic | Statement: [Dougga, inscriptionLanguage, Neo-Punic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neo-Punic Context triple: [Dougga, inscriptionLanguage, Neo-Punic]
-
A.
Punic script
chosen
Punic script is a later, regionally adapted form of the Phoenician writing system used primarily in Carthage and other Punic-speaking communities around the western Mediterranean.
-
B.
Sabaic
Sabaic is an ancient South Arabian Semitic language once used in inscriptions and documents in what is now Yemen.
-
C.
Phoenician language
The Phoenician language was an ancient Northwest Semitic tongue, written in a consonantal alphabet that became the ancestor of many later writing systems, including Greek and Latin scripts.
-
D.
Judeo-Roman
Judeo-Roman is a historical Jewish dialect of the Italian language traditionally spoken by the Jewish community of Rome.
-
E.
Numidia
Numidia was an ancient Berber kingdom in North Africa that became a significant power and later a Roman client and province.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a493599a0081908da65f3407af1ef2 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a66ab4608190afcd81e6606c5116 |
completed | March 1, 2026, 8:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a66673d6288190bb6a68c6c376016e |
completed | March 3, 2026, 4:41 a.m. |
Created at: March 1, 2026, 7:37 p.m.