Triple
T7707876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skomer Island |
E174667
|
entity |
| Predicate | nearestTown |
P350
|
FINISHED |
| Object | Marloes |
E607368
|
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: Marloes | Statement: [Skomer Island, nearestTown, Marloes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marloes Context triple: [Skomer Island, nearestTown, Marloes]
-
A.
Saskia
Saskia is a female given name of Germanic origin, most famously borne by Saskia van Uylenburgh, the wife and frequent model of the Dutch painter Rembrandt.
-
B.
Jolanda
Jolanda is a feminine given name, commonly considered a variant of Yolanda, used in various European countries.
-
C.
Marlies
Marlies is the common nickname for the Toronto Marlboros, a historic Canadian junior ice hockey team based in Toronto.
-
D.
Marloes Sands
chosen
Marloes Sands is a scenic, expansive sandy beach in Pembrokeshire, Wales, known for its dramatic cliffs, rock formations, and coastal walks.
-
E.
Saskia de Jonge
Saskia de Jonge is a Dutch former competitive swimmer who specialized in freestyle events and represented the Netherlands in international competitions, including the Olympic Games.
- 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_69c6995b3e8c8190833108f883d5f53c |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c702aadea08190bf827f5d51535224 |
completed | March 27, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8acc896008190bacae1ae79498103 |
completed | March 29, 2026, 4:38 a.m. |
Created at: March 27, 2026, 4:04 p.m.