Triple

T15330936
Position Surface form Disambiguated ID Type / Status
Subject Kupa E366528 entity
Predicate hasTributary P415 FINISHED
Object Kupčina
Kupčina is a river in central Croatia that serves as one of the tributaries of the Kupa River.
E1150069 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: Kupčina | Statement: [Kupa, hasTributary, Kupčina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kupčina
Context triple: [Kupa, hasTributary, Kupčina]
  • A. Kapesovo
    Kapesovo is a traditional stone-built village in the Zagori region of Epirus, Greece, known for its preserved architecture and scenic mountainous setting.
  • B. Kupenite
    Kupenite is a group of rugged mountain peaks in Bulgaria’s Rila Mountains, popular with climbers and hikers for their steep rocky profiles and alpine scenery.
  • C. Kukoč
    Kukoč is the surname of Toni Kukoč, a renowned Croatian basketball player and three-time NBA champion with the Chicago Bulls.
  • D. Kopaska
    Kopaska is the Indonesian Navy’s elite frogman and special operations unit, specializing in underwater demolition, maritime sabotage, and counter-terrorism missions.
  • E. Kosere
    "Kosere" is a popular Nigerian song by singer CDQ, known for its energetic Afrobeat style and street-influenced lyrics.
  • 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: Kupčina
Triple: [Kupa, hasTributary, Kupčina]
Generated description
Kupčina is a river in central Croatia that serves as one of the tributaries of the Kupa River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kupčina
Target entity description: Kupčina is a river in central Croatia that serves as one of the tributaries of the Kupa River.
  • A. Kapesovo
    Kapesovo is a traditional stone-built village in the Zagori region of Epirus, Greece, known for its preserved architecture and scenic mountainous setting.
  • B. Kupenite
    Kupenite is a group of rugged mountain peaks in Bulgaria’s Rila Mountains, popular with climbers and hikers for their steep rocky profiles and alpine scenery.
  • C. Kukoč
    Kukoč is the surname of Toni Kukoč, a renowned Croatian basketball player and three-time NBA champion with the Chicago Bulls.
  • D. Kopaska
    Kopaska is the Indonesian Navy’s elite frogman and special operations unit, specializing in underwater demolition, maritime sabotage, and counter-terrorism missions.
  • E. Kosere
    "Kosere" is a popular Nigerian song by singer CDQ, known for its energetic Afrobeat style and street-influenced lyrics.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e0161ac8190aa1d52c063c02ad0 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8b1b2d08190a158bf65535ad750 completed May 9, 2026, 9:04 a.m.
NEDg Description generation batch_69fefb10ba78819094948f5401702e79 completed May 9, 2026, 9:14 a.m.
NED2 Entity disambiguation (via description) batch_69fefbad7de08190aa2479ec0243e3a6 completed May 9, 2026, 9:17 a.m.
Created at: April 10, 2026, 3:17 a.m.