Triple

T13263848
Position Surface form Disambiguated ID Type / Status
Subject Karlovac County E315865 entity
Predicate hasSettlement P1068 FINISHED
Object Tounj
Tounj is a small town and municipality in central Croatia known for its historic stone bridge and surrounding karst landscape.
E1030820 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: Tounj | Statement: [Karlovac County, hasSettlement, Tounj]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tounj
Context triple: [Karlovac County, hasSettlement, Tounj]
  • A. Tourtour
    Tourtour is a picturesque hilltop village in southeastern France, often called the "village in the sky" for its elevated views over Provence.
  • B. Tuni
    Tuni is a town in the East Godavari district of Andhra Pradesh, India, known as a regional commercial and transportation hub.
  • C. Lebou
    The Lebou are a coastal West African ethnic group primarily found around Dakar, Senegal, known historically as skilled fishermen and early urban settlers of the Cap-Vert Peninsula.
  • D. Khenchela
    Khenchela is a town in northeastern Algeria known as an important urban center in the Aurès mountain region.
  • E. Béja
    Béja is a historic city in northwestern Tunisia known for its agricultural importance and Roman-era heritage.
  • 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: Tounj
Triple: [Karlovac County, hasSettlement, Tounj]
Generated description
Tounj is a small town and municipality in central Croatia known for its historic stone bridge and surrounding karst landscape.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tounj
Target entity description: Tounj is a small town and municipality in central Croatia known for its historic stone bridge and surrounding karst landscape.
  • A. Tourtour
    Tourtour is a picturesque hilltop village in southeastern France, often called the "village in the sky" for its elevated views over Provence.
  • B. Tuni
    Tuni is a town in the East Godavari district of Andhra Pradesh, India, known as a regional commercial and transportation hub.
  • C. Lebou
    The Lebou are a coastal West African ethnic group primarily found around Dakar, Senegal, known historically as skilled fishermen and early urban settlers of the Cap-Vert Peninsula.
  • D. Khenchela
    Khenchela is a town in northeastern Algeria known as an important urban center in the Aurès mountain region.
  • E. Béja
    Béja is a historic city in northwestern Tunisia known for its agricultural importance and Roman-era heritage.
  • 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_69d806b1d9ac8190852c5571d5bd5f0f completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9901c65048190bd8b3c4872f22520 completed April 11, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a48bc488190a5cf692d81bdcbba completed May 3, 2026, 8:41 a.m.
NEDg Description generation batch_69f70b5dbcc4819081b5ba410e319eb7 completed May 3, 2026, 8:46 a.m.
NED2 Entity disambiguation (via description) batch_69f70c4c6f908190b2ebc2a90b049e59 completed May 3, 2026, 8:50 a.m.
Created at: April 9, 2026, 9:25 p.m.