Triple
T22715149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metropolitan area of Taranto |
E561708
|
entity |
| Predicate | hasMunicipality |
P847
|
FINISHED |
| Object | Laterza |
E528059
|
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: Laterza | Statement: [Metropolitan area of Taranto, hasMunicipality, Laterza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laterza Context triple: [Metropolitan area of Taranto, hasMunicipality, Laterza]
-
A.
Laterza
chosen
Laterza is a town and comune in the Apulia region of southern Italy, known for its historic center, traditional ceramics, and proximity to the Gravina di Laterza canyon.
-
B.
Caselotti
Caselotti is an Italian surname most notably associated with Adriana Caselotti, the original voice of Snow White in Disney’s 1937 animated film.
-
C.
Lazzara
Lazzara is the birth surname of acclaimed American actress and singer Bernadette Peters.
-
D.
Longiano
Longiano is a historic hilltop town in Italy’s Emilia-Romagna region, known for its medieval castle, scenic views, and well-preserved old center.
-
E.
Malvestiti
Malvestiti is an Italian surname most notably associated with Piero Malvestiti, a mid-20th-century Italian politician and European statesman.
- 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_69e2454f1348819088d83f420925a5c1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790ca59881909064d49f331fb711 |
completed | April 29, 2026, 3:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b8fbe82fc8190a783458a6aba1f6b |
completed | May 18, 2026, 10:16 p.m. |
Created at: April 17, 2026, 3:18 p.m.