Triple
T19164965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ilha do Maio |
E469154
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Porto Inglês port |
—
|
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: Porto Inglês port | Statement: [Ilha do Maio, hasPort, Porto Inglês port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porto Inglês port Context triple: [Ilha do Maio, hasPort, Porto Inglês port]
-
A.
Porto Inglês
chosen
Porto Inglês is the main town and port on the Cape Verdean island of Maio, known for its colonial architecture and coastal setting.
-
B.
English Port
English Port is a coastal harbor settlement historically associated with English maritime activity, likely serving as a trading or anchorage point.
-
C.
Mar Português
Mar Português is a celebrated poem by Fernando Pessoa that reflects on Portugal’s maritime history, national identity, and the spiritual legacy of its Age of Discoveries.
-
D.
Portuguesa
Portuguesa is a state in western Venezuela known for its extensive agricultural production, particularly of rice and corn, earning it the nickname "the Granary of Venezuela."
-
E.
Portuguese: Enseada de Inhaúma
Enseada de Inhaúma is a coastal inlet located in the city of Rio de Janeiro, Brazil.
- 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f15e2720819084b1707497db26a2 |
completed | April 20, 2026, 9:26 a.m. |
Created at: April 10, 2026, 12:06 p.m.