Triple
T21174831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neapolis Archaeological Park |
E521783
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Latomia di Santa Venera |
—
|
NE NERFINISHED |
How this triple was built (3 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: Latomia di Santa Venera | Statement: [Neapolis Archaeological Park, contains, Latomia di Santa Venera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Latomia di Santa Venera Context triple: [Neapolis Archaeological Park, contains, Latomia di Santa Venera]
-
A.
Santa Venera
Santa Venera is a small urban town in central Malta known for its residential character and proximity to the capital, Valletta.
-
B.
Mtarfa
Mtarfa is a small historic town in central Malta known for its former British military barracks, clock tower, and panoramic views over the surrounding countryside.
-
C.
Cittadella, Gozo
Cittadella, Gozo is a historic fortified citadel overlooking Victoria on the Maltese island of Gozo, known for its medieval architecture and panoramic views.
-
D.
Sliema
Sliema is a coastal town in Malta known for its seafront promenade, shopping, and role as a major residential and commercial hub near the capital Valletta.
-
E.
Mozia
Mozia is an ancient Phoenician island settlement off the western coast of Sicily, renowned for its archaeological remains and historical significance in Mediterranean trade.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Latomia di Santa Venera Target entity description: Latomia di Santa Venera is an ancient stone quarry in Syracuse, Sicily, historically used for extracting limestone and later as a prison, now preserved as part of the Neapolis Archaeological Park.
-
A.
Santa Venera
Santa Venera is a small urban town in central Malta known for its residential character and proximity to the capital, Valletta.
-
B.
Mtarfa
Mtarfa is a small historic town in central Malta known for its former British military barracks, clock tower, and panoramic views over the surrounding countryside.
-
C.
Cittadella, Gozo
Cittadella, Gozo is a historic fortified citadel overlooking Victoria on the Maltese island of Gozo, known for its medieval architecture and panoramic views.
-
D.
Sliema
Sliema is a coastal town in Malta known for its seafront promenade, shopping, and role as a major residential and commercial hub near the capital Valletta.
-
E.
Mozia
Mozia is an ancient Phoenician island settlement off the western coast of Sicily, renowned for its archaeological remains and historical significance in Mediterranean trade.
- F. None of above. chosen
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_69e0b50e30748190b186824a206d39b9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7271597288190b04baff9ca8d866c |
completed | April 21, 2026, 7:28 a.m. |
Created at: April 16, 2026, 3 p.m.