Triple
T32227040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decorated Farmhouses of Hälsingland |
E823229
|
entity |
| Predicate | UNESCOSessionCity |
P55222
|
FINISHED |
| Object | Saint Petersburg |
—
|
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: Saint Petersburg | Statement: [Decorated Farmhouses of Hälsingland, UNESCOSessionCity, Saint Petersburg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UNESCOSessionCity Context triple: [Decorated Farmhouses of Hälsingland, UNESCOSessionCity, Saint Petersburg]
-
A.
UNESCOSessionLocation
chosen
Indicates the location where a particular UNESCO session is held or took place.
-
B.
UNESCOSessionCountry
Indicates that a given country participated in or was represented at a particular UNESCO session.
-
C.
UNESCOCreativeCityCategory
Indicates that a city is designated by UNESCO as belonging to a specific category within the UNESCO Creative Cities Network (e.g., music, literature, design).
-
D.
UNESCOSessionOfInscription
Indicates the specific UNESCO session during which an item was formally inscribed or added to a UNESCO list.
-
E.
connectsHeritageCities
Indicates a relationship in which one entity links or provides a route between two or more heritage cities, enabling connection or interaction among them.
- 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_69f3490b4f948190b99e4f999f5be25f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bbcca23c8190913df3c818b52fbb |
completed | May 3, 2026, 3:06 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:38 a.m.