Triple
T18890196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anagnia |
E462064
|
entity |
| Predicate | culture |
P1114
|
FINISHED |
| Object | Italic |
—
|
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: Italic | Statement: [Anagnia, culture, Italic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Italic Context triple: [Anagnia, culture, Italic]
-
A.
Italic
Italic is a branch of the Indo-European language family that includes Latin and its descendants, such as the Romance languages.
-
B.
Italic world
chosen
The Italic world refers to the mosaic of ancient peoples, languages, and cultures that inhabited the Italian Peninsula before and during the rise of Rome.
-
C.
Old Italic script
Old Italic script is an ancient family of writing systems used on the Italian peninsula, from which the Latin alphabet ultimately evolved.
-
D.
Linea Gotica
Linea Gotica was a major German defensive line in northern Italy during World War II, designed to halt the Allied advance through the Italian peninsula.
-
E.
Arial
Arial is a widely used sans-serif typeface known for its clean, modern appearance and extensive use in digital and print media.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c479f3208190a9d665865c4b630b |
completed | April 20, 2026, 6:15 a.m. |
Created at: April 10, 2026, 11:58 a.m.