Triple
T16089486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line A (Prague Metro) |
E390322
|
entity |
| Predicate | interchangeStation |
P15892
|
FINISHED |
| Object | Muzeum |
E390324
|
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: Muzeum | Statement: [Line A (Prague Metro), interchangeStation, Muzeum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Muzeum Context triple: [Line A (Prague Metro), interchangeStation, Muzeum]
-
A.
Muzeum
chosen
Muzeum is a major interchange station in the Prague Metro system, located beneath Wenceslas Square and serving as a key hub for lines A and C.
-
B.
The Museum
The Museum is an art exhibition space within Tokyo’s Bunkamura cultural complex, known for hosting a wide range of domestic and international art shows.
-
C.
Museon
Museon is a science and culture museum in The Hague, Netherlands, known for its interactive exhibits on nature, technology, and world cultures.
-
D.
Zepter Museum
The Zepter Museum is a private art museum in Belgrade, Serbia, showcasing modern and contemporary Serbian and Yugoslav art.
-
E.
Museumsufer
Museumsufer is Frankfurt am Main’s renowned museum district along the River Main, known for its dense concentration of major art, cultural, and historical museums.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1845161908190adca2af94710b2cc |
completed | April 17, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb934b448190a486401ac6c01065 |
completed | May 10, 2026, 2:21 a.m. |
Created at: April 10, 2026, 4:59 a.m.