Triple
T12347812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hradčany |
E294402
|
entity |
| Predicate | hasNameInGerman |
P22792
|
FINISHED |
| Object |
Hradschin
Hradschin is the German name for Hradčany, the historic castle district of Prague dominated by Prague Castle.
|
E977647
|
NE FINISHED |
How this triple was built (4 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: Hradschin | Statement: [Hradčany, hasNameInGerman, Hradschin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hradschin Context triple: [Hradčany, hasNameInGerman, Hradschin]
-
A.
Sendlinger Tor
Sendlinger Tor is a historic city gate in Munich, Germany, and one of the remaining medieval entrances to the old town.
-
B.
Altkönig
Altkönig is a prominent mountain peak in Germany’s Taunus range, known for its scenic hiking trails and remains of ancient Celtic fortifications.
-
C.
Spremberger Turm
Spremberger Turm is a historic medieval city tower and prominent architectural landmark in the German city of Cottbus.
-
D.
Kufstein Fortress
Kufstein Fortress is a medieval hilltop stronghold in Kufstein, Austria, known for its well-preserved fortifications and panoramic views over the town and surrounding Alps.
-
E.
Berchtesgadener Hochthron
Berchtesgadener Hochthron is a prominent alpine peak in the Berchtesgaden Alps of Bavaria, Germany, known for its panoramic views and popular hiking and climbing routes.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hradschin Triple: [Hradčany, hasNameInGerman, Hradschin]
Generated description
Hradschin is the German name for Hradčany, the historic castle district of Prague dominated by Prague Castle.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hradschin Target entity description: Hradschin is the German name for Hradčany, the historic castle district of Prague dominated by Prague Castle.
-
A.
Sendlinger Tor
Sendlinger Tor is a historic city gate in Munich, Germany, and one of the remaining medieval entrances to the old town.
-
B.
Altkönig
Altkönig is a prominent mountain peak in Germany’s Taunus range, known for its scenic hiking trails and remains of ancient Celtic fortifications.
-
C.
Spremberger Turm
Spremberger Turm is a historic medieval city tower and prominent architectural landmark in the German city of Cottbus.
-
D.
Kufstein Fortress
Kufstein Fortress is a medieval hilltop stronghold in Kufstein, Austria, known for its well-preserved fortifications and panoramic views over the town and surrounding Alps.
-
E.
Berchtesgadener Hochthron
Berchtesgadener Hochthron is a prominent alpine peak in the Berchtesgaden Alps of Bavaria, Germany, known for its panoramic views and popular hiking and climbing routes.
- F. None of above. chosen
Provenance (5 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7ba17481908b03af7316b28d9b |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62aae8d7c8190a722c28a5a153d1d |
completed | May 2, 2026, 4:47 p.m. |
| NEDg | Description generation | batch_69f62c569a6c8190aecf8a4c627d8893 |
completed | May 2, 2026, 4:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f62d0c2568819083e66c8ae484d30d |
completed | May 2, 2026, 4:57 p.m. |
Created at: April 8, 2026, 9:53 p.m.