Triple
T14266123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gesundbrunnen |
E353647
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Humboldthain Park |
E610251
|
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: Humboldthain Park | Statement: [Gesundbrunnen, hasLandmark, Humboldthain Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Humboldthain Park Context triple: [Gesundbrunnen, hasLandmark, Humboldthain Park]
-
A.
Humboldthain park
chosen
Humboldthain Park is a large urban green space in Berlin known for its World War II-era flak tower ruins, panoramic viewpoints, and extensive recreational areas.
-
B.
Heston Park
Heston Park is a public green space and recreational park located in the Heston area of the London Borough of Hounslow, England.
-
C.
Peasholm Park
Peasholm Park is a historic oriental-themed public park and popular tourist attraction in Scarborough, North Yorkshire, known for its boating lake and landscaped gardens.
-
D.
Woodhouse Park
Woodhouse Park is a residential neighbourhood within the Wythenshawe district of Manchester, England.
-
E.
George Green Park
George Green Park is a public recreational park located in Anoka, Minnesota, offering outdoor green space and amenities for community use.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6357a8188190ba518a486521052b |
completed | April 14, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd7a31ef388190bc3082abc1c25ff4 |
completed | May 8, 2026, 5:52 a.m. |
Created at: April 10, 2026, 1:09 a.m.