Triple
T14889141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Woolston |
E359706
|
entity |
| Predicate | hasNearbyArea |
P4647
|
FINISHED |
| Object | Sholing |
E350406
|
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: Sholing | Statement: [Woolston, hasNearbyArea, Sholing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sholing Context triple: [Woolston, hasNearbyArea, Sholing]
-
A.
Sholing
chosen
Sholing is a residential suburb in the eastern part of Southampton, England, known for its housing estates, local schools, and community amenities.
-
B.
Port Dickson
Port Dickson is a coastal resort town in Malaysia known for its beaches and seaside tourism along the Strait of Malacca.
-
C.
Marina Bay
Marina Bay is a waterfront neighborhood and marina district in Richmond, California, known for its residential developments, shoreline parks, and views of the San Francisco Bay.
-
D.
Kranji
Kranji is a largely rural area in northwestern Singapore known for its nature reserves, farms, and military memorials.
-
E.
Willingdon Island
Willingdon Island is a major artificial island in Kochi, India, known as a key hub for the region’s port, naval, and commercial activities.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded5f6cf5c8190b6b28f58fafe5d59 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b61407481908a618d14c56d2abf |
completed | May 8, 2026, 11:01 p.m. |
Created at: April 10, 2026, 2:09 a.m.