Triple
T10731238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marsamxett Harbour |
E253078
|
entity |
| Predicate | adjacentTown |
P3883
|
FINISHED |
| Object | Gżira |
E275183
|
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: Gżira | Statement: [Marsamxett Harbour, adjacentTown, Gżira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gżira Context triple: [Marsamxett Harbour, adjacentTown, Gżira]
-
A.
Gżira
chosen
Gżira is a coastal town in central Malta known for its marina, views of Valletta, and proximity to the popular Sliema and Manoel Island areas.
-
B.
Żejtun
Żejtun is a historic town in southeastern Malta known for its traditional architecture, olive-growing heritage, and prominent parish church.
-
C.
Mezzegra
Mezzegra is a small village and former municipality on the western shore of Lake Como in the Lombardy region of northern Italy.
-
D.
Aurisina
Aurisina is a village in northeastern Italy’s Friuli Venezia Giulia region, known for its karst landscape and proximity to the Adriatic coast near Trieste.
-
E.
Enza
Enza is a river in northern Italy that flows through the Emilia-Romagna region before joining the Secchia.
- 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_69d6aa5d8be481909a43218b2bfdbe95 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d70fcb1cd881909635def59ad5d19c |
completed | April 9, 2026, 2:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dbda1d1b108190a47b46661bc85b2d |
completed | April 12, 2026, 5:45 p.m. |
Created at: April 8, 2026, 9:14 p.m.