Triple
T14500565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berkeley |
E359622
|
entity |
| Predicate | hasPark |
P105
|
FINISHED |
| Object |
Holborn Park
Holborn Park is a public green space in Berkeley, California, offering local residents recreational areas and outdoor amenities.
|
E1116679
|
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: Holborn Park | Statement: [Berkeley, hasPark, Holborn Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holborn Park Context triple: [Berkeley, hasPark, Holborn Park]
-
A.
Holland Park
Holland Park is a leafy, affluent district and public park in west London known for its elegant townhouses, landscaped gardens, and cultural attractions.
-
B.
Westbourne Park
Westbourne Park is a residential and commercial area in West London, known for its Victorian terraces and proximity to Notting Hill and Portobello Road.
-
C.
Green Park
Green Park is a central London royal park known for its open lawns, mature trees, and tranquil atmosphere between Buckingham Palace and Piccadilly.
-
D.
Green Park
Green Park is a public park in Kanpur, India, historically significant enough to lend its name to the nearby Green Park Stadium.
-
E.
Green Park
Green Park is a Delhi Metro station in South Delhi serving the Green Park and nearby Hauz Khas and Safdarjung 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: Holborn Park Triple: [Berkeley, hasPark, Holborn Park]
Generated description
Holborn Park is a public green space in Berkeley, California, offering local residents recreational areas and outdoor amenities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Holborn Park Target entity description: Holborn Park is a public green space in Berkeley, California, offering local residents recreational areas and outdoor amenities.
-
A.
Holland Park
Holland Park is a leafy, affluent district and public park in west London known for its elegant townhouses, landscaped gardens, and cultural attractions.
-
B.
Westbourne Park
Westbourne Park is a residential and commercial area in West London, known for its Victorian terraces and proximity to Notting Hill and Portobello Road.
-
C.
Green Park
Green Park is a central London royal park known for its open lawns, mature trees, and tranquil atmosphere between Buckingham Palace and Piccadilly.
-
D.
Green Park
Green Park is a public park in Kanpur, India, historically significant enough to lend its name to the nearby Green Park Stadium.
-
E.
Green Park
Green Park is a Delhi Metro station in South Delhi serving the Green Park and nearby Hauz Khas and Safdarjung 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de94dfe484819086dd971606e6478e |
completed | April 14, 2026, 7:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdfb7543f88190ac336c75188eb00a |
completed | May 8, 2026, 3:04 p.m. |
| NEDg | Description generation | batch_69fdfe396bb48190ade10c757a3a7e5e |
completed | May 8, 2026, 3:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdfeb5d08081908ff0fdbc489fc985 |
completed | May 8, 2026, 3:18 p.m. |
Created at: April 10, 2026, 1:21 a.m.