Triple
T9147381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | north-west Kent |
E219491
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Greenhithe |
E212183
|
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: Greenhithe | Statement: [north-west Kent, containsTown, Greenhithe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greenhithe Context triple: [north-west Kent, containsTown, Greenhithe]
-
A.
Greenhithe
chosen
Greenhithe is a village in Kent, England, known for its proximity to the River Thames and major retail and transport hubs in the Dartford area.
-
B.
Hythe
Hythe is a small village in northwestern Alberta, Canada, situated west of the city of Grande Prairie.
-
C.
Hythe
Hythe is a historic coastal town in Kent, England, known as one of the original Cinque Ports that once played a key role in maritime defense and trade.
-
D.
Brightlingsea
Brightlingsea is a coastal town in Essex, England, historically known for its maritime trade, shipbuilding, and association with the medieval Cinque Ports confederation.
-
E.
Baslehurst
Baslehurst is a fictional English town that serves as the primary setting in Anthony Trollope’s novel "Rachel Ray."
- 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_69ca83e121dc81909912bd66953081c5 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca918a3c881909c34a6a682eb2625 |
completed | April 1, 2026, 5:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0482995cc81909bfc202cbab7f8a1 |
completed | April 3, 2026, 11:07 p.m. |
Created at: March 30, 2026, 7:20 p.m.