Triple
T3304172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verdun, France |
E69406
|
entity |
| Predicate | twinnedWith |
P1072
|
FINISHED |
| Object | Salisbury |
E87538
|
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: Salisbury | Statement: [Verdun, France, twinnedWith, Salisbury]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salisbury Context triple: [Verdun, France, twinnedWith, Salisbury]
-
A.
Salisbury
Salisbury is the former colonial-era name of Zimbabwe’s capital city, now known as Harare.
-
B.
Salisbury
chosen
Salisbury is a historic cathedral city in Wiltshire, England, renowned for its medieval architecture and proximity to the ancient monument of Stonehenge.
-
C.
Carlisle
Carlisle is a historic cathedral city and county town of Cumbria in North West England, near the Scottish border.
-
D.
Carlisle
Carlisle is a historic borough in south-central Pennsylvania known for its military education institutions, colonial heritage, and role in the American Revolutionary era.
-
E.
Dover
Dover is a small town in eastern Dutchess County, New York, known for its rural character and location near the Connecticut border.
- 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0c8179081908a2595d1fdb7560a |
completed | March 8, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b32507bc808190b9c3fce4c456b0aa |
completed | March 12, 2026, 8:41 p.m. |
Created at: March 8, 2026, 3:11 p.m.