Triple
T20181900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torfaen valley |
E492748
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Ponthir |
—
|
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: Ponthir | Statement: [Torfaen valley, containsSettlement, Ponthir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ponthir Context triple: [Torfaen valley, containsSettlement, Ponthir]
-
A.
Ponthir
chosen
Ponthir is a small village in South Wales, situated near Cwmbran and Newport within the county borough of Torfaen.
-
B.
Chenu
Chenu is a commune in northwestern France, located in the Sarthe department of the Pays de la Loire region.
-
C.
Teraina
Teraina is a remote, low-lying coral atoll in the central Pacific Ocean that forms part of the Republic of Kiribati.
-
D.
Gannat
Gannat is a small town in central France known for its rich paleontological heritage and traditional cultural festivals.
-
E.
Pouni
Pouni is a town in the Reasi district of the Jammu and Kashmir region of India, serving as one of its local commercial and administrative centers.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668ef9370819091a8479f811002a9 |
completed | April 20, 2026, 5:57 p.m. |
Created at: April 11, 2026, 11:36 p.m.