Triple
T14161547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Factory Cove |
E350958
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Moe Island |
—
|
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: Moe Island | Statement: [Factory Cove, near, Moe Island]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Moe Island Context triple: [Factory Cove, near, Moe Island]
-
A.
Moe Island
chosen
Moe Island is a small, remote island in the South Orkney Islands of the Southern Ocean, noted for its harsh polar climate and importance as a protected wildlife habitat.
-
B.
Funye Island
Funye Island is one of the principal islands in Uganda’s Ssese Archipelago on Lake Victoria, known for its natural scenery and relative remoteness.
-
C.
Metoma Island
Metoma Island is a small island in the Torres Islands group of northern Vanuatu in the South Pacific Ocean.
-
D.
Talahi Island
Talahi Island is a small coastal island community in Chatham County, Georgia, located near Savannah along the state’s southeastern shoreline.
-
E.
Mason Island
Mason Island is a notable island located in the Potomac River, recognized as one of its significant river islands.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61393f308190bb357e2bd1916f94 |
completed | April 14, 2026, 3:46 p.m. |
Created at: April 10, 2026, 12:59 a.m.