Triple
T11574448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Metal Cross |
E274467
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Dixcove |
E577149
|
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: Dixcove | Statement: [Fort Metal Cross, locatedIn, Dixcove]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dixcove Context triple: [Fort Metal Cross, locatedIn, Dixcove]
-
A.
Dixcove
chosen
Dixcove is a coastal fishing town in southwestern Ghana known for its historic fort and role in regional maritime trade.
-
B.
Dugwor
Dugwor is a dialect of the Mwaghavul language spoken by a subgroup of the Mwaghavul people in Nigeria.
-
C.
Dushore
Dushore is a small borough in Sullivan County, Pennsylvania, known as a local commercial and community hub in a largely rural, mountainous region.
-
D.
Mauregard
Mauregard is a small commune in the Seine-et-Marne department of the Île-de-France region in north-central France, situated near Paris Charles de Gaulle Airport.
-
E.
Valderice
Valderice is a small town and comune in western Sicily, Italy, known for its scenic hillside setting near the historic city of Erice and views over the Gulf of Trapani.
- 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d89048120c81908258f984711f7dd4 |
completed | April 10, 2026, 5:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e713e49f508190b9bad316d68eab42 |
completed | April 21, 2026, 6:06 a.m. |
Created at: April 8, 2026, 9:38 p.m.