Triple
T16899106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danube promenade (Szentendre) |
E424386
|
entity |
| Predicate | languageOfTouristInformation |
P116984
|
FINISHED |
| Object | Hungarian |
—
|
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: Hungarian | Statement: [Danube promenade (Szentendre), languageOfTouristInformation, Hungarian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfTouristInformation Context triple: [Danube promenade (Szentendre), languageOfTouristInformation, Hungarian]
-
A.
languageOfOfficialGuides
Indicates the language in which official guides or instructional materials are provided or published.
-
B.
languageOfInformationCenter
chosen
Indicates the language in which an information center communicates or provides its information resources.
-
C.
languageUsedInTourism
Indicates that a particular language is used for communication and services within tourism activities or contexts.
-
D.
languageOfOfficialAnnouncements
Indicates the language used for formal or official public announcements issued by an authority.
-
E.
officialLanguageOfSignage
Indicates that a particular language is the one officially used on public signs and signage within a given place or context.
- 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_69d889da3e8c8190a2b118f383f0beac |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3c8da7b0481909111358871875023 |
completed | April 18, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69e32b9489408190bcb2ede567ff5bf9 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:29 a.m.