Triple
T1725670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh Marches Line |
E37489
|
entity |
| Predicate | startPoint |
P389
|
FINISHED |
| Object | Newport |
E39916
|
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: Newport | Statement: [Welsh Marches Line, startPoint, Newport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Newport Context triple: [Welsh Marches Line, startPoint, Newport]
-
A.
Newport
Newport is a coastal city in Oregon known for its fishing industry, marine science centers, and scenic Pacific shoreline.
-
B.
Newport
chosen
Newport is a major city in South Wales known as an important industrial and port center on the River Usk.
-
C.
Newport
Newport is a leading menthol cigarette brand in the United States, known for its strong market presence and association with menthol-flavored tobacco products.
-
D.
Newport
Newport is the principal town and administrative center of the Isle of Wight, located near the middle of the island in southern England.
-
E.
Newport
Newport is the former name of Parkersburg, a city located along the Ohio River in western West Virginia.
- 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_69a8861acab88190bb43cde203429399 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa635cad5481908e6c04a230d3b0bb |
completed | March 6, 2026, 5:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b030e23ea081909737f5fd2d3c8dfb |
completed | March 10, 2026, 2:55 p.m. |
Created at: March 4, 2026, 7:30 p.m.