Triple

T9685764
Position Surface form Disambiguated ID Type / Status
Subject Zagyva E234402 entity
Predicate hasTributary P415 FINISHED
Object Tarna
Tarna is a river in northern Hungary that serves as one of the tributaries feeding into the Zagyva River.
 E815339 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: Tarna | Statement: [Zagyva, hasTributary, Tarna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tarna
Context triple: [Zagyva, hasTributary, Tarna]
  • A. Tauri
    Tauri were an ancient people of the Crimean Peninsula, known from Greek and Roman sources for their distinct culture and coastal strongholds around the Black Sea.
  • B. Marulan
    Marulan is a small town in New South Wales, Australia, known as a rural service centre located near the geographic midpoint between Sydney and Canberra.
  • C. Tynaarlo
    Tynaarlo is a municipality in the northeastern Netherlands known for its rural character and location between the cities of Groningen and Assen.
  • D. Teron
    Teron is one of the traditional clans of the Karbi people, an indigenous ethnic group primarily inhabiting the Karbi Anglong region of Assam in Northeast India.
  • E. Krakhuna
    Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
  • 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: Tarna
Triple: [Zagyva, hasTributary, Tarna]
Generated description
Tarna is a river in northern Hungary that serves as one of the tributaries feeding into the Zagyva River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tarna
Target entity description: Tarna is a river in northern Hungary that serves as one of the tributaries feeding into the Zagyva River.
  • A. Tauri
    Tauri were an ancient people of the Crimean Peninsula, known from Greek and Roman sources for their distinct culture and coastal strongholds around the Black Sea.
  • B. Marulan
    Marulan is a small town in New South Wales, Australia, known as a rural service centre located near the geographic midpoint between Sydney and Canberra.
  • C. Tynaarlo
    Tynaarlo is a municipality in the northeastern Netherlands known for its rural character and location between the cities of Groningen and Assen.
  • D. Teron
    Teron is one of the traditional clans of the Karbi people, an indigenous ethnic group primarily inhabiting the Karbi Anglong region of Assam in Northeast India.
  • E. Krakhuna
    Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
  • 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_69ca84ca73208190957a900c8543bdcc completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9cd2dab481908e0d3fed28de9d40 completed April 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1910b7c148190b9061b1ce0520e8b completed April 4, 2026, 10:30 p.m.
NEDg Description generation batch_69d193150c00819080ed0fbb050b60bf completed April 4, 2026, 10:39 p.m.
NED2 Entity disambiguation (via description) batch_69d19416efd48190865d0178e5e893fa completed April 4, 2026, 10:43 p.m.
Created at: March 30, 2026, 8:16 p.m.