Triple
T8909480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deal railway station |
E212143
|
entity |
| Predicate | hasServiceTo |
P6787
|
FINISHED |
| Object | Sandwich |
E64008
|
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: Sandwich | Statement: [Deal railway station, hasServiceTo, Sandwich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandwich Context triple: [Deal railway station, hasServiceTo, Sandwich]
-
A.
Sandwich
Sandwich is a historic town on Cape Cod in Massachusetts, known as one of the oldest settlements in New England and a popular coastal tourist destination.
-
B.
SANDWICH
chosen
SANDWICH is a historic town in Kent, England, known as one of the best-preserved medieval towns in the country.
-
C.
BLT
BLT is a Swiss public transport company that operates tram and bus services in and around the Basel region.
-
D.
Bread
"Bread" is a historical novel by Russian writer Alexei Tolstoy that depicts the tumultuous events of the Russian Civil War and the early Soviet period.
-
E.
Bread
Bread was a popular American soft rock band of the 1970s known for mellow, melodic hits like "Make It with You" and "Everything I Own."
- 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_69ca839255248190b43984294abd92ae |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc65207bbc8190be181555b9564797 |
completed | April 1, 2026, 12:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba36f8cc8190ab57ddc99b7219d1 |
completed | April 3, 2026, 1:01 p.m. |
Created at: March 30, 2026, 6:55 p.m.