Triple

T3846346
Position Surface form Disambiguated ID Type / Status
Subject Vyšehrad E93578 entity
Predicate hasPart P35 FINISHED
Object Leopold Gate
Leopold Gate is a historic Baroque entrance gate in the Vyšehrad fortress complex in Prague, Czech Republic.
 E393453 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: Leopold Gate | Statement: [Vyšehrad, hasPart, Leopold Gate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Leopold Gate
Context triple: [Vyšehrad, hasPart, Leopold Gate]
  • A. Florian Gate
    Florian Gate is a historic medieval city gate in Kraków, Poland, and one of the best-preserved remnants of the city’s old defensive walls.
  • B. Londorossi Gate
    Londorossi Gate is a primary western entrance and registration point to Mount Kilimanjaro National Park, commonly used by climbers beginning the Lemosho Route.
  • C. Erer Gate
    Erer Gate is one of the historic gateways in the ancient walled city of Harar Jugol in eastern Ethiopia.
  • D. Kröpeliner Tor
    Kröpeliner Tor is a historic medieval city gate and prominent architectural landmark in the German city of Rostock.
  • E. Borovitsky Gate
    Borovitsky Gate is a historic entrance to the Moscow Kremlin complex, situated by the Borovitskaya Tower and serving as one of the main access points to the fortress.
  • 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: Leopold Gate
Triple: [Vyšehrad, hasPart, Leopold Gate]
Generated description
Leopold Gate is a historic Baroque entrance gate in the Vyšehrad fortress complex in Prague, Czech Republic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Leopold Gate
Target entity description: Leopold Gate is a historic Baroque entrance gate in the Vyšehrad fortress complex in Prague, Czech Republic.
  • A. Florian Gate
    Florian Gate is a historic medieval city gate in Kraków, Poland, and one of the best-preserved remnants of the city’s old defensive walls.
  • B. Londorossi Gate
    Londorossi Gate is a primary western entrance and registration point to Mount Kilimanjaro National Park, commonly used by climbers beginning the Lemosho Route.
  • C. Erer Gate
    Erer Gate is one of the historic gateways in the ancient walled city of Harar Jugol in eastern Ethiopia.
  • D. Kröpeliner Tor
    Kröpeliner Tor is a historic medieval city gate and prominent architectural landmark in the German city of Rostock.
  • E. Borovitsky Gate
    Borovitsky Gate is a historic entrance to the Moscow Kremlin complex, situated by the Borovitskaya Tower and serving as one of the main access points to the fortress.
  • 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_69aed96ce578819084ab16e3439976c9 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeebb77a488190be7fc2a1211f1f2d completed March 9, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b504122cb08190ba97ce14e8d891fc completed March 14, 2026, 6:45 a.m.
NEDg Description generation batch_69b504a31de08190b543549a2b05b038 completed March 14, 2026, 6:48 a.m.
NED2 Entity disambiguation (via description) batch_69b5084c8bd48190b7afc80bed196c90 completed March 14, 2026, 7:03 a.m.
Created at: March 9, 2026, 3:18 p.m.