Triple
T22088708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince of Altamura |
E545854
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Altamura |
—
|
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: Altamura | Statement: [Prince of Altamura, locatedIn, Altamura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Altamura Context triple: [Prince of Altamura, locatedIn, Altamura]
-
A.
Altamura
chosen
Altamura is a historic town in the Apulia region of southern Italy, renowned for its well-preserved medieval center and its traditional DOP-certified Altamura bread.
-
B.
Sontra
Sontra is a small town in the Werra-Meißner district of northeastern Hesse, Germany, known for its rural setting and proximity to the Richelsdorf Hills.
-
C.
Montelusa
Montelusa is a fictional Sicilian city in Andrea Camilleri’s Inspector Montalbano series, loosely based on the real town of Agrigento.
-
D.
Tarquinia
Tarquinia is an ancient Etruscan city in central Italy renowned for its richly painted tombs and significant archaeological remains.
-
E.
Patavium
Patavium is the ancient Roman name for the city now known as Padua in northern Italy, historically an important urban and cultural center of the Veneto region.
- 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_69e11e36d03c8190a83a1ba802b7231b |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128e3a98481908a7b3dc3f2a90276 |
completed | April 28, 2026, 9:38 p.m. |
Created at: April 16, 2026, 8:29 p.m.