Triple
T23385768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Area, Sierra Leone |
E593874
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Freetown Harbour |
—
|
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: Freetown Harbour | Statement: [Western Area, Sierra Leone, contains, Freetown Harbour]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Freetown Harbour Context triple: [Western Area, Sierra Leone, contains, Freetown Harbour]
-
A.
Sekondi Harbour
Sekondi Harbour is a seaport in Sekondi-Takoradi, Ghana, serving as an important hub for maritime trade and regional shipping.
-
B.
Port of Freetown
chosen
The Port of Freetown is Sierra Leone’s principal deep-water seaport and a key maritime hub for trade and shipping in West Africa.
-
C.
Freetown
Freetown is the capital and largest city of Sierra Leone, known as a historic port and former center for resettled freed slaves in West Africa.
-
D.
Freetown
Freetown is a historic rural town in Bristol County, southeastern Massachusetts, known for its forests, ponds, and the reputedly haunted Freetown-Fall River State Forest.
-
E.
Port of Banjul
The Port of Banjul is The Gambia’s principal seaport and a key maritime gateway for trade and cargo handling in the country and the wider West African region.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a498286c8190abfa381649812cf0 |
completed | April 29, 2026, 6:26 a.m. |
Created at: April 17, 2026, 5:35 p.m.