Triple

T19466518
Position Surface form Disambiguated ID Type / Status
Subject City of Vienne E487013 entity
Predicate twinTown P1072 FINISHED
Object Zabki
Ząbki is a small town in eastern Poland, located near Warsaw and known as a residential suburb of the capital.
 E1377164 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: Zabki | Statement: [City of Vienne, twinTown, Zabki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zabki
Context triple: [City of Vienne, twinTown, Zabki]
  • A. Zabana
    Zabana is an Oceanic language spoken in the Solomon Islands, primarily on Santa Isabel Island.
  • B. Izberbash
    Izberbash is a coastal city on the Caspian Sea in the Republic of Dagestan, Russia, known for its fishing industry and role as a regional transport and economic center.
  • C. Z Boku
    Z Boku is a monumental abstract sculpture by artist Ursula von Rydingsvard, known for her large-scale, textured cedar-wood forms.
  • D. Zazas
    The Zazas are an Iranian ethnic group primarily inhabiting eastern Turkey, known for speaking the Zaza (Dimili) language and maintaining distinct cultural traditions.
  • E. Zabban
    Zabban is an alternate given name of Abu Amr ibn al-Ala, a prominent early Islamic scholar and one of the canonical readers of the Qur’an.
  • 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: Zabki
Triple: [City of Vienne, twinTown, Zabki]
Generated description
Ząbki is a small town in eastern Poland, located near Warsaw and known as a residential suburb of the capital.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zabki
Target entity description: Ząbki is a small town in eastern Poland, located near Warsaw and known as a residential suburb of the capital.
  • A. Zabana
    Zabana is an Oceanic language spoken in the Solomon Islands, primarily on Santa Isabel Island.
  • B. Izberbash
    Izberbash is a coastal city on the Caspian Sea in the Republic of Dagestan, Russia, known for its fishing industry and role as a regional transport and economic center.
  • C. Z Boku
    Z Boku is a monumental abstract sculpture by artist Ursula von Rydingsvard, known for her large-scale, textured cedar-wood forms.
  • D. Zazas
    The Zazas are an Iranian ethnic group primarily inhabiting eastern Turkey, known for speaking the Zaza (Dimili) language and maintaining distinct cultural traditions.
  • E. Zabban
    Zabban is an alternate given name of Abu Amr ibn al-Ala, a prominent early Islamic scholar and one of the canonical readers of the Qur’an.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633e1dccc819096feb1a514b9eb86 completed April 20, 2026, 2:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a073b40271c8190a27b00e6533ed1a0 completed May 15, 2026, 3:26 p.m.
NEDg Description generation batch_6a073c19c3b88190a6114d272ebd5fbc completed May 15, 2026, 3:30 p.m.
NED2 Entity disambiguation (via description) batch_6a073d25ba448190a62777b68d2f3136 completed May 15, 2026, 3:35 p.m.
Created at: April 10, 2026, 1:39 p.m.