Triple

T18067145
Position Surface form Disambiguated ID Type / Status
Subject Lika E432321 entity
Predicate containsTown P847 FINISHED
Object Perušić
Perušić is a small town in the Lika region of Croatia, known for its rural setting, historical architecture, and proximity to natural attractions such as caves and forests.
 E1303590 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: Perušić | Statement: [Lika, containsTown, Perušić]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Perušić
Context triple: [Lika, containsTown, Perušić]
  • A. Mijatović
    Mijatović is a South Slavic surname, common in countries such as Serbia, Bosnia and Herzegovina, and Croatia, borne by various notable figures in politics, sports, and the arts.
  • B. Perišić
    Perišić is a South Slavic surname, most commonly found in Serbia, Croatia, and neighboring countries.
  • C. Zoran
    Zoran is a masculine given name commonly used in several Slavic countries, particularly in the Balkans.
  • D. Danilo Türk
    Danilo Türk is a Slovenian diplomat, international law expert, and politician who served as the country's president in the late 2000s and early 2010s.
  • E. Veljko Bulajić
    Veljko Bulajić is a renowned Yugoslav and Croatian film director best known for his large-scale World War II epics and internationally acclaimed partisan films.
  • 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: Perušić
Triple: [Lika, containsTown, Perušić]
Generated description
Perušić is a small town in the Lika region of Croatia, known for its rural setting, historical architecture, and proximity to natural attractions such as caves and forests.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Perušić
Target entity description: Perušić is a small town in the Lika region of Croatia, known for its rural setting, historical architecture, and proximity to natural attractions such as caves and forests.
  • A. Mijatović
    Mijatović is a South Slavic surname, common in countries such as Serbia, Bosnia and Herzegovina, and Croatia, borne by various notable figures in politics, sports, and the arts.
  • B. Perišić
    Perišić is a South Slavic surname, most commonly found in Serbia, Croatia, and neighboring countries.
  • C. Zoran
    Zoran is a masculine given name commonly used in several Slavic countries, particularly in the Balkans.
  • D. Danilo Türk
    Danilo Türk is a Slovenian diplomat, international law expert, and politician who served as the country's president in the late 2000s and early 2010s.
  • E. Veljko Bulajić
    Veljko Bulajić is a renowned Yugoslav and Croatian film director best known for his large-scale World War II epics and internationally acclaimed partisan films.
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4cce97ce08190a2f8762ce545e091 completed April 19, 2026, 12:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a035670159081909bc8c626318253a2 completed May 12, 2026, 4:33 p.m.
NEDg Description generation batch_6a03576c04e881908f76694f053d709a completed May 12, 2026, 4:38 p.m.
NED2 Entity disambiguation (via description) batch_6a0357f78a7c819083d57f330083698e completed May 12, 2026, 4:40 p.m.
Created at: April 10, 2026, 10:26 a.m.