Triple
T9805437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thorn |
E237941
|
entity |
| Predicate | culturalSpecialty |
P83906
|
FINISHED |
| Object | gingerbread (Toruń gingerbread) |
—
|
LITERAL 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: gingerbread (Toruń gingerbread) | Statement: [Thorn, culturalSpecialty, gingerbread (Toruń gingerbread)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: culturalSpecialty Context triple: [Thorn, culturalSpecialty, gingerbread (Toruń gingerbread)]
-
A.
culturalElements
chosen
Indicates a relationship where certain elements (such as practices, symbols, or artifacts) belong to, express, or characterize a particular culture or cultural context.
-
B.
culturalType
Indicates the classification of something according to its cultural category, style, or tradition.
-
C.
culturalCategory
Indicates that one entity classifies or groups another entity according to a particular culture, tradition, or culturally defined type.
-
D.
culturalExport
Indicates that something originating in one culture is transmitted, adopted, or influential in another culture or region.
-
E.
intangibleHeritageDomain
Indicates that something belongs to, or is categorized within, a specific domain or category of intangible cultural heritage.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab7b67748190ba16ce868f29d13e |
completed | April 1, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.