Triple
T3366790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A6 road |
E70855
|
entity |
| Predicate | passesThrough |
P225
|
FINISHED |
| Object | Derby |
E53520
|
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: Derby | Statement: [A6 road, passesThrough, Derby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derby Context triple: [A6 road, passesThrough, Derby]
-
A.
Derby
chosen
Derby is a historic city in Derbyshire, England, known for its industrial heritage, particularly in railways and engineering.
-
B.
Derby
Derby is a neighborhood within the Brazilian city of Recife, known for its central location and urban character.
-
C.
Derby
Derby is a small historic city in Connecticut known for its location at the confluence of the Housatonic and Naugatuck Rivers and its industrial heritage.
-
D.
Derby
Derby is a small coastal town in Western Australia's Kimberley region, known as a gateway to the outback and for its large tidal variations and proximity to the Buccaneer Archipelago.
-
E.
Derby City
Derby City is a popular nickname for Louisville, Kentucky, reflecting the city's fame as home of the Kentucky Derby horse race.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb287a30c8190b4c40091675c94fb |
completed | March 8, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b325500eac8190b6f43864af8bda6c |
completed | March 12, 2026, 8:42 p.m. |
Created at: March 8, 2026, 3:13 p.m.