Triple
T18911191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aberkenfig |
E462609
|
entity |
| Predicate | hasNeighbouringSettlement |
P4647
|
FINISHED |
| Object | Tondu |
—
|
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: Tondu | Statement: [Aberkenfig, hasNeighbouringSettlement, Tondu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tondu Context triple: [Aberkenfig, hasNeighbouringSettlement, Tondu]
-
A.
Tondu
chosen
Tondu is a village in Bridgend County Borough, South Wales, historically known for its coal mining and ironworks industries.
-
B.
Calvatone
Calvatone is a small municipality in the Lombardy region of northern Italy, known for its rural landscape and proximity to the Oglio River.
-
C.
Toffia
Toffia is a small historic hilltop town in the Lazio region of central Italy, known for its medieval architecture and scenic countryside setting.
-
D.
Topuz
Topuz is the surname of the pioneering Turkish novelist and intellectual Fatma Aliye.
-
E.
Tozzer
Tozzer is a surname most notably associated with Alfred Marston Tozzer, an American anthropologist and archaeologist known for his pioneering work on Mayan civilization.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c6226f4081909b77aac26c574980 |
completed | April 20, 2026, 6:22 a.m. |
Created at: April 10, 2026, 11:58 a.m.