Triple
T19340155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gretna Green railway station |
E483729
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Gretna |
—
|
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: Gretna | Statement: [Gretna Green railway station, nearbySettlement, Gretna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gretna Context triple: [Gretna Green railway station, nearbySettlement, Gretna]
-
A.
Gretna
chosen
Gretna is a small Scottish town near the England–Scotland border, historically famous as a destination for runaway weddings.
-
B.
Gretna
Gretna is a small but rapidly growing city in eastern Nebraska, known for its convenient location near Omaha and attractions like the Nebraska Crossing outlet mall.
-
C.
Gretna, Louisiana
Gretna, Louisiana is a small city in Jefferson Parish, part of the New Orleans metropolitan area, known as a local governmental and judicial center.
-
D.
Gretna, Virginia
Gretna, Virginia is a small incorporated town in southern Virginia known for its rural character and location within Pittsylvania County.
-
E.
Gainneville
Gainneville is a French commune in the Seine-Maritime department of Normandy, situated near the port city of Le Havre.
- 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_69d8e8d244f8819080eb1f3491300db2 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e618560f0081908565f802ea1e3cc8 |
completed | April 20, 2026, 12:13 p.m. |
Created at: April 10, 2026, 1:33 p.m.