Triple

T15774704
Position Surface form Disambiguated ID Type / Status
Subject Upper Morava Valley E382459 entity
Predicate containsTown P847 FINISHED
Object Uničov
Uničov is a historic town in the Olomouc Region of the Czech Republic, known as one of the country’s oldest royal towns with a well-preserved medieval center.
E1175632 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: Uničov | Statement: [Upper Morava Valley, containsTown, Uničov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uničov
Context triple: [Upper Morava Valley, containsTown, Uničov]
  • A. Udava
    Udava is a river in eastern Slovakia that serves as a tributary of the Laborec River.
  • B. Junkovac
    Junkovac is a small settlement located within the municipality of Lazarevac in Serbia.
  • C. Rušanj
    Rušanj is a suburban settlement of Belgrade, Serbia, located within the municipality of Čukarica.
  • D. Valtice
    Valtice is a historic town in the South Moravian Region of the Czech Republic, renowned for its Baroque chateau, vineyards, and role as a key part of the Lednice–Valtice cultural landscape.
  • E. Njeguši
    Njeguši is a historic Montenegrin village in the mountains of the Lovćen region, renowned as the birthplace of the Petrović-Njegoš dynasty and for its traditional smoked ham and cheese.
  • 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: Uničov
Triple: [Upper Morava Valley, containsTown, Uničov]
Generated description
Uničov is a historic town in the Olomouc Region of the Czech Republic, known as one of the country’s oldest royal towns with a well-preserved medieval center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Uničov
Target entity description: Uničov is a historic town in the Olomouc Region of the Czech Republic, known as one of the country’s oldest royal towns with a well-preserved medieval center.
  • A. Udava
    Udava is a river in eastern Slovakia that serves as a tributary of the Laborec River.
  • B. Junkovac
    Junkovac is a small settlement located within the municipality of Lazarevac in Serbia.
  • C. Rušanj
    Rušanj is a suburban settlement of Belgrade, Serbia, located within the municipality of Čukarica.
  • D. Valtice
    Valtice is a historic town in the South Moravian Region of the Czech Republic, renowned for its Baroque chateau, vineyards, and role as a key part of the Lednice–Valtice cultural landscape.
  • E. Njeguši
    Njeguši is a historic Montenegrin village in the mountains of the Lovćen region, renowned as the birthplace of the Petrović-Njegoš dynasty and for its traditional smoked ham and cheese.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e05198c1588190a65e23c18443eb5c completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff877e67b881908a67b9acc79d998f completed May 9, 2026, 7:14 p.m.
NEDg Description generation batch_69ff88358e408190a8d7424fc495d4fa completed May 9, 2026, 7:17 p.m.
NED2 Entity disambiguation (via description) batch_69ff88f192a08190acbc2c3fc98c65c8 completed May 9, 2026, 7:20 p.m.
Created at: April 10, 2026, 4:47 a.m.