Triple
T11346221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Exuma Island |
E268719
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Williams Town |
E889960
|
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: Williams Town | Statement: [Little Exuma Island, hasSettlement, Williams Town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Williams Town Context triple: [Little Exuma Island, hasSettlement, Williams Town]
-
A.
Williams Town
chosen
Williams Town is a small settlement located on Little Exuma in The Bahamas, known for its quiet beaches and traditional island character.
-
B.
King’s Town
King’s Town is the former name of Kingston, the capital and largest city of Jamaica.
-
C.
Francistown
Francistown is a major city in northeastern Botswana, historically known as a gold-mining center and an important commercial hub near the border with Zimbabwe.
-
D.
Stewarttown
Stewarttown is a small community located within the town of Halton Hills in Ontario, Canada.
-
E.
Shingletown
Shingletown is a small rural community in Northern California known for its forested setting near Lassen Volcanic National Park.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea1f9574819089760c5b5908f09e |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e58b8d5f5c8190a80a52f2063bb5b0 |
completed | April 20, 2026, 2:12 a.m. |
Created at: April 8, 2026, 9:33 p.m.