Triple
T8125700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hassocks |
E189722
|
entity |
| Predicate | hasRecreationGround |
P5383
|
FINISHED |
| Object |
Adastra Park
Adastra Park is a public recreational park and sports ground in the village of Hassocks in West Sussex, England.
|
E755618
|
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: Adastra Park | Statement: [Hassocks, hasRecreationGround, Adastra Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adastra Park Context triple: [Hassocks, hasRecreationGround, Adastra Park]
-
A.
Yıldız Park
Yıldız Park is a large historic urban park in Istanbul, Turkey, known for its wooded hills, Ottoman-era pavilions, and views over the Bosphorus.
-
B.
Kalorama Park
Kalorama Park is a neighborhood green space in Washington, D.C., known for its playgrounds, recreation areas, and role as a community gathering spot in the Kalorama area.
-
C.
Ceres Park
Ceres Park is a multi-purpose stadium in Aarhus, Denmark, primarily used for football and home to the Danish club AGF.
-
D.
Topstone Park
Topstone Park is a natural recreational area in Redding, Connecticut, known for its wooded trails, swimming pond, and outdoor activities.
-
E.
Pascone Park
Pascone Park is a local public park in the village of Ardsley, New York, offering recreational green space and community amenities for residents.
- 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: Adastra Park Triple: [Hassocks, hasRecreationGround, Adastra Park]
Generated description
Adastra Park is a public recreational park and sports ground in the village of Hassocks in West Sussex, England.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Adastra Park Target entity description: Adastra Park is a public recreational park and sports ground in the village of Hassocks in West Sussex, England.
-
A.
Yıldız Park
Yıldız Park is a large historic urban park in Istanbul, Turkey, known for its wooded hills, Ottoman-era pavilions, and views over the Bosphorus.
-
B.
Kalorama Park
Kalorama Park is a neighborhood green space in Washington, D.C., known for its playgrounds, recreation areas, and role as a community gathering spot in the Kalorama area.
-
C.
Ceres Park
Ceres Park is a multi-purpose stadium in Aarhus, Denmark, primarily used for football and home to the Danish club AGF.
-
D.
Topstone Park
Topstone Park is a natural recreational area in Redding, Connecticut, known for its wooded trails, swimming pond, and outdoor activities.
-
E.
Pascone Park
Pascone Park is a local public park in the village of Ardsley, New York, offering recreational green space and community amenities for residents.
- 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_69ca82bb74848190afb1f18640632c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb438eb778819085296e6cbfa2e70d |
completed | March 31, 2026, 3:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf421875f88190a005c3ffba04dffe |
completed | April 3, 2026, 4:29 a.m. |
| NEDg | Description generation | batch_69cf43ead588819094089bea94c27207 |
completed | April 3, 2026, 4:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cf453fa3e4819082466c59649c2f35 |
completed | April 3, 2026, 4:42 a.m. |
Created at: March 30, 2026, 5:34 p.m.