Triple
T19687667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Purgatory |
E472753
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Earthly Paradise |
—
|
NE NERFINISHED |
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: Earthly Paradise | Statement: [Mount Purgatory, hasPart, Earthly Paradise]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Earthly Paradise Context triple: [Mount Purgatory, hasPart, Earthly Paradise]
-
A.
Earthly Paradise
chosen
Earthly Paradise is the idyllic, sinless garden at the summit of Mount Purgatory in Dante’s Divine Comedy, symbolizing humanity’s original innocence and the threshold to Heaven.
-
B.
Paradise Found
Paradise Found is a jazz-influenced vocal and guitar album by the American duo Tuck & Patti, showcasing their intimate, soulful style and intricate arrangements.
-
C.
The Paradise
The Paradise is a British period drama television series set in a 19th-century department store, focusing on the lives, romances, and ambitions of its staff and customers.
-
D.
Paradise
Paradise is the eternal, blissful abode in the hereafter promised by Allah to the righteous in Islamic belief.
-
E.
Paradise
Paradise is a photographic series by German artist Thomas Struth that features large-scale, detailed images of lush, unspoiled natural landscapes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6420d39688190ad3a84dbffce4ffe |
completed | April 20, 2026, 3:11 p.m. |
Created at: April 10, 2026, 1:45 p.m.