Triple
T19158816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ħamrun |
E468996
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Marsa |
—
|
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: Marsa | Statement: [Ħamrun, near, Marsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marsa Context triple: [Ħamrun, near, Marsa]
-
A.
Marsa
chosen
Marsa is a town in Malta located on the shores of the Grand Harbour, known historically for its port and industrial facilities.
-
B.
Marsa al-Brega
Marsa al-Brega is a coastal industrial town in northeastern Libya known for its major oil refinery and petrochemical facilities on the Gulf of Sidra.
-
C.
La Marsa
La Marsa is a coastal suburb of Tunis in northern Tunisia, known for its beaches, upscale residential areas, and historic seaside charm.
-
D.
Corisco
Corisco is a small island in the Gulf of Guinea, off the coast of Equatorial Guinea, historically significant as a site of European—particularly Spanish—presence and regional trade.
-
E.
Ammoudia
Ammoudia is a small coastal village in northwestern Greece, known for its sandy beach and location at the mouth of the Acheron River.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eebb573081909fcd6af8aff8692b |
completed | April 20, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:06 p.m.