Triple
T28545414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Varese |
E722421
|
entity |
| Predicate | hasUNESCOSiteOnIsland |
P2499
|
FINISHED |
| Object | Isolino Virginia |
—
|
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: Isolino Virginia | Statement: [Lake Varese, hasUNESCOSiteOnIsland, Isolino Virginia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUNESCOSiteOnIsland Context triple: [Lake Varese, hasUNESCOSiteOnIsland, Isolino Virginia]
-
A.
hasUNESCOCandidateSite
Indicates that an entity possesses or includes at least one site that is a candidate for inscription on the UNESCO World Heritage List.
-
B.
hasHeritageCityOnIsland
Indicates that a heritage city is located on, or geographically situated on, an island.
-
C.
hasWorldHeritageSite
chosen
Indicates that a location or entity possesses or contains a site designated as a UNESCO World Heritage Site.
-
D.
UNESCOWorldHeritageSiteRelated
Indicates a relationship where one entity is designated as, part of, or otherwise officially associated with a UNESCO World Heritage Site.
-
E.
UNESCOWorldHeritageSiteWithin
Indicates that a UNESCO World Heritage Site is geographically located within the boundaries of a specified area or region.
- F. None of above.
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_69f01a5e42348190b1ffbca26e739c84 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 28, 2026, 3:38 a.m.