Triple
T7248677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Liner |
E156539
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Port Island |
E62455
|
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: Port Island | Statement: [Port Liner, serves, Port Island]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Port Island Context triple: [Port Liner, serves, Port Island]
-
A.
Port Island
chosen
Port Island is a large man-made island and urban district in Kobe, Japan, known for its port facilities, business centers, and residential areas built on reclaimed land.
-
B.
Port Royal Island
Port Royal Island is a sea island in Beaufort County, South Carolina, known for its historic Lowcountry communities, coastal landscapes, and role in early American and Civil War history.
-
C.
Boston Island
Boston Island is a small island off the coast of Port Lincoln in South Australia, known for its coastal scenery and wildlife.
-
D.
Harbor Island
Harbor Island is a man-made peninsula in San Diego, California, known for its marinas, waterfront hotels, and views of the downtown skyline and bay.
-
E.
Harbor Island
Harbor Island is a large artificial industrial island in Seattle, Washington, situated at the mouth of the Duwamish River.
- 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_69c68827b5e481908dc05e145b2c92d4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea763f208190af1210cd8d2a05c9 |
completed | March 27, 2026, 8:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c81eaf59988190a656dae4e588c496 |
completed | March 28, 2026, 6:32 p.m. |
Created at: March 27, 2026, 2:56 p.m.