Triple
T17449487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Helena garrison |
E424875
|
entity |
| Predicate | country |
P26
|
FINISHED |
| Object | Saint Helena |
—
|
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: Saint Helena | Statement: [Saint Helena garrison, country, Saint Helena]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint Helena Context triple: [Saint Helena garrison, country, Saint Helena]
-
A.
Saint Helena
chosen
Saint Helena is a remote volcanic island in the South Atlantic Ocean, best known as the place of Napoleon Bonaparte’s exile and death.
-
B.
Saint Helena
Saint Helena is a Christian saint traditionally credited with finding the True Cross and known as the mother of the Roman Emperor Constantine the Great.
-
C.
St. Helena
St. Helena is a small, historic city in California’s Napa Valley known for its wineries, vineyards, and upscale culinary and tourism scene.
-
D.
St Helena Island
St Helena Island is a small island in Queensland’s Moreton Bay best known for its 19th-century penal colony and well-preserved historic ruins.
-
E.
St. Helena Island
St. Helena Island is a historic sea island in South Carolina known for its rich Gullah Geechee culture, African American heritage, and coastal landscapes.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4513b99908190a6b5833559856c8b |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 10, 2026, 5:47 a.m.