Triple
T14866414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hősök tere |
E349626
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Városliget |
E349632
|
NE 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: Városliget | Statement: [Hősök tere, adjacentTo, Városliget]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Városliget Context triple: [Hősök tere, adjacentTo, Városliget]
-
A.
Városliget
chosen
Városliget is a large public city park in Budapest, Hungary, known for its cultural attractions, recreational spaces, and historic landmarks.
-
B.
Boshof
Boshof is a small town in South Africa’s Free State province, historically known for its agricultural economy and role in the Anglo-Boer War.
-
C.
Muhos
Muhos is a municipality in Northern Ostrobothnia, Finland, known for its riverside landscapes along the Oulujoki and its proximity to the city of Oulu.
-
D.
Parádsasvár
Parádsasvár is a small village in northern Hungary known for its scenic Mátra mountain surroundings and historic glassworks and castle.
-
E.
Párkány
Párkány is a town on the Danube River in southern Slovakia, near the Hungarian border, historically known as a strategic site of conflicts between the Habsburg and Ottoman empires.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d822ed7e1881909b90fca143ad7e34 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded5761c688190b4477cb081554b51 |
completed | April 15, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b5101a48190937a86b6eda79c55 |
completed | May 8, 2026, 11:01 p.m. |
Created at: April 10, 2026, 1:55 a.m.