Triple
T16359300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maddalena Archipelago |
E397268
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Santa Maria |
E955376
|
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: Santa Maria | Statement: [Maddalena Archipelago, hasIsland, Santa Maria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Santa Maria Context triple: [Maddalena Archipelago, hasIsland, Santa Maria]
-
A.
Santa Maria
Santa Maria is a city in California’s Central Coast region known for its agriculture, wine industry, and distinctive Santa Maria–style barbecue.
-
B.
Santa Maria
Santa Maria is a popular sandy beach on the Greek island of Paros, known for its clear waters, water sports, and lively summer atmosphere.
-
C.
Santa Maria
Santa Maria is a coastal town on the southern tip of Sal Island in Cape Verde, known for its sandy beaches, tourism, and water sports.
-
D.
Santa Maria
Santa Maria is a major city in southern Brazil known as an educational and military center in the state of Rio Grande do Sul.
-
E.
Santa Maria
chosen
Santa Maria is one of the small islands located within the Stagnone Lagoon off the western coast of Sicily, Italy.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2fad1859c819082b47bf9d7fabd9f |
completed | April 18, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002dbce2508190b655de87f48e841e |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:07 a.m.