Triple
T22687241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Newhaven |
E560948
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Western Port |
—
|
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: Western Port | Statement: [Newhaven, locatedOn, Western Port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Western Port Context triple: [Newhaven, locatedOn, Western Port]
-
A.
Western Port
chosen
Western Port is a large tidal bay and natural harbor in southern Victoria, Australia, known for its islands, wetlands, and coastal wildlife.
-
B.
Sandy Bay
Sandy Bay is a coastal area on the western side of Hong Kong Island, known for its residential neighborhoods, sports facilities, and proximity to the University of Hong Kong.
-
C.
Sandy Bay
Sandy Bay is a popular surf beach and coastal area on New Zealand’s Tutukaka Coast, known for its scenic shoreline and consistent waves.
-
D.
Sandy Bay
Sandy Bay is a popular sandy beach and holiday destination on the coast of Devon, England.
-
E.
Sandy Bay
Sandy Bay is a coastal suburb of Hobart, Tasmania, known for its waterfront, residential areas, and proximity to the city centre.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178649aac8190a9d41f5d82895bdf |
completed | April 29, 2026, 3:17 a.m. |
Created at: April 17, 2026, 3:13 p.m.