Triple
T13929772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MOD Boscombe Down |
E334958
|
entity |
| Predicate | garrison |
P75
|
FINISHED |
| Object | Boscombe Down |
E767161
|
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: Boscombe Down | Statement: [MOD Boscombe Down, garrison, Boscombe Down]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boscombe Down Context triple: [MOD Boscombe Down, garrison, Boscombe Down]
-
A.
Boscombe Down
chosen
Boscombe Down is a major British military airfield and aircraft testing site in Wiltshire, England.
-
B.
Bagshot Heath
Bagshot Heath is an extensive area of heathland in Surrey, England, known for its open, sandy terrain, wildlife habitats, and use for military training and outdoor recreation.
-
C.
Marlborough Downs
Marlborough Downs is a broad expanse of rolling chalk downland in Wiltshire, England, known for its open landscapes, prehistoric sites, and rich archaeological heritage.
-
D.
Bembridge Down
Bembridge Down is a chalk downland area on the Isle of Wight in England, known for its open grassland, coastal views, and historical features including military remains.
-
E.
Weedon Field
Weedon Field is a public-use airport serving the city of Eufaula in southeastern Alabama.
- 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_69d81c5f739081908bc05b2461f54828 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2aa900a0819095eeb1bc46b0336e |
completed | April 14, 2026, 11:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce8262288190a7e6dd647b1917c1 |
completed | May 3, 2026, 10:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.