Triple
T8346951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth River |
E196063
|
entity |
| Predicate | hasFacility |
P105
|
FINISHED |
| Object | Craney Island |
E688117
|
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: Craney Island | Statement: [Elizabeth River, hasFacility, Craney Island]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Craney Island Context triple: [Elizabeth River, hasFacility, Craney Island]
-
A.
Craney Island
chosen
Craney Island is a small island in Virginia notable as the site of an 1813 War of 1812 battle in which American forces successfully repelled a British attack.
-
B.
Dunham Island
Dunham Island is a small island located within Oneida Lake in central New York State.
-
C.
Digby Island
Digby Island is a small island on the north coast of British Columbia, Canada, situated near the city of Prince Rupert and serving as the site of the region’s main airport.
-
D.
Muggs Island
Muggs Island is a small, wooded island within Toronto’s offshore island chain, known for its natural setting and limited development.
-
E.
Fannette Island
Fannette Island is the only island in Lake Tahoe, known for its picturesque setting in Emerald Bay and the ruins of a small stone teahouse on its summit.
- 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_69ca82edd63c8190b876b8465464c5fa |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb8013d81c81908da48466cffb3939 |
completed | March 31, 2026, 8:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf5127db38819087d5ba71b6064998 |
completed | April 3, 2026, 5:33 a.m. |
Created at: March 30, 2026, 5:58 p.m.