Triple

T9251377
Position Surface form Disambiguated ID Type / Status
Subject Iława E222330 entity
Predicate hasLake P1025 FINISHED
Object Jeziorak
Jeziorak is a long, narrow lake in northern Poland, known as one of the country's largest and a popular destination for water sports and recreation.
E787635 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: Jeziorak | Statement: [Iława, hasLake, Jeziorak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeziorak
Context triple: [Iława, hasLake, Jeziorak]
  • A. Jezer
    Jezer is a minor biblical figure mentioned in the Hebrew Bible as one of the descendants associated with the tribe of Naphtali.
  • B. Rybi Potok
    Rybi Potok is a mountain stream in the Tatra Mountains of southern Poland that drains the waters of the popular alpine lake Morskie Oko.
  • C. Bóbrka
    Bóbrka is a village in southeastern Poland historically significant as one of the birthplaces of the modern oil industry.
  • D. Skawina
    Skawina is a town in southern Poland near Kraków, known for its industrial facilities and role as a local economic and transport hub.
  • E. Fiala
    Fiala is a Czech surname most prominently associated with Petr Fiala, the Czech politician and Prime Minister.
  • 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: Jeziorak
Triple: [Iława, hasLake, Jeziorak]
Generated description
Jeziorak is a long, narrow lake in northern Poland, known as one of the country's largest and a popular destination for water sports and recreation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jeziorak
Target entity description: Jeziorak is a long, narrow lake in northern Poland, known as one of the country's largest and a popular destination for water sports and recreation.
  • A. Jezer
    Jezer is a minor biblical figure mentioned in the Hebrew Bible as one of the descendants associated with the tribe of Naphtali.
  • B. Rybi Potok
    Rybi Potok is a mountain stream in the Tatra Mountains of southern Poland that drains the waters of the popular alpine lake Morskie Oko.
  • C. Bóbrka
    Bóbrka is a village in southeastern Poland historically significant as one of the birthplaces of the modern oil industry.
  • D. Skawina
    Skawina is a town in southern Poland near Kraków, known for its industrial facilities and role as a local economic and transport hub.
  • E. Fiala
    Fiala is a Czech surname most prominently associated with Petr Fiala, the Czech politician and Prime Minister.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd05f9ade48190ac8425a1c6f066b1 completed April 1, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0780650648190bc85452678268134 completed April 4, 2026, 2:31 a.m.
NEDg Description generation batch_69d080275cdc8190bb900671756bacb8 completed April 4, 2026, 3:06 a.m.
NED2 Entity disambiguation (via description) batch_69d080c936348190a3bfda72ff5ec5c0 completed April 4, 2026, 3:08 a.m.
Created at: March 30, 2026, 7:31 p.m.