Triple
T10975919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leagrave |
E259368
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object |
Sundon Park
Sundon Park is a residential suburb and housing estate in the north of Luton, Bedfordshire, England.
|
E901911
|
NE FINISHED |
How this triple was built (4 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: Sundon Park | Statement: [Leagrave, adjacentTo, Sundon Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sundon Park Context triple: [Leagrave, adjacentTo, Sundon Park]
-
A.
Upton Park
Upton Park is a district in East London best known for being the longtime home area of West Ham United’s former stadium, the Boleyn Ground.
-
B.
Wanstead Park
Wanstead Park is a railway station in east London serving the Gospel Oak to Barking line, close to the green spaces of Wanstead Flats and Wanstead Park.
-
C.
Woking Park
Woking Park is a public recreational park in Woking, England, featuring green spaces, sports facilities, and community amenities.
-
D.
Millward Park
Millward Park is a local public park located in the city of Allen Park, Michigan, offering outdoor recreational space for residents and visitors.
-
E.
Carshalton Park
Carshalton Park is a public green space in the London suburb of Carshalton, known for its historic features, open lawns, and community recreation areas.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sundon Park Triple: [Leagrave, adjacentTo, Sundon Park]
Generated description
Sundon Park is a residential suburb and housing estate in the north of Luton, Bedfordshire, England.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sundon Park Target entity description: Sundon Park is a residential suburb and housing estate in the north of Luton, Bedfordshire, England.
-
A.
Upton Park
Upton Park is a district in East London best known for being the longtime home area of West Ham United’s former stadium, the Boleyn Ground.
-
B.
Wanstead Park
Wanstead Park is a railway station in east London serving the Gospel Oak to Barking line, close to the green spaces of Wanstead Flats and Wanstead Park.
-
C.
Woking Park
Woking Park is a public recreational park in Woking, England, featuring green spaces, sports facilities, and community amenities.
-
D.
Millward Park
Millward Park is a local public park located in the city of Allen Park, Michigan, offering outdoor recreational space for residents and visitors.
-
E.
Carshalton Park
Carshalton Park is a public green space in the London suburb of Carshalton, known for its historic features, open lawns, and community recreation areas.
- F. None of above. chosen
Provenance (5 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d771f4e888819097433271a2f45ff3 |
completed | April 9, 2026, 9:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a954a1f481908c5653b8ddb09164 |
completed | April 18, 2026, 3:55 p.m. |
| NEDg | Description generation | batch_69e3ad00b5c08190a7bf3ecbeae76d88 |
completed | April 18, 2026, 4:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e3b1efe4a88190884eb5186954cf39 |
completed | April 18, 2026, 4:31 p.m. |
Created at: April 8, 2026, 9:24 p.m.