Triple
T13247946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vyšehrad Cemetery |
E315453
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Prague 2 |
E393450
|
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: Prague 2 | Statement: [Vyšehrad Cemetery, locatedIn, Prague 2]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prague 2 Context triple: [Vyšehrad Cemetery, locatedIn, Prague 2]
-
A.
Prague 2
chosen
Prague 2 is a central district of Prague, Czech Republic, known for its historic neighborhoods, parks, and landmarks such as Vyšehrad.
-
B.
Prague 3
Prague 3 is a central district of Prague known for its historic neighborhoods, including Žižkov, and notable cultural and religious sites such as the New Jewish Cemetery.
-
C.
Prague 17
Prague 17 is a municipal district of Prague, Czech Republic, located on the western edge of the city and encompassing primarily residential neighborhoods.
-
D.
Prague 1
Prague 1 is the historic central district of Prague, encompassing many of the city’s most famous landmarks, government buildings, and tourist attractions.
-
E.
42 Prague
42 Prague is a tuition-free, peer-to-peer programming school in the Czech Republic that follows the innovative, project-based learning model of the international 42 network.
- 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d9e7ea881908abc4b3a54896692 |
completed | April 10, 2026, 11:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6ff37f7448190b9c555cae010d3b6 |
completed | May 3, 2026, 7:54 a.m. |
Created at: April 9, 2026, 9:24 p.m.