Triple

T18618673
Position Surface form Disambiguated ID Type / Status
Subject Wollo E455093 entity
Predicate hasCity P316 FINISHED
Object Hayq
Hayq is a town in Ethiopia’s Amhara Region, known for its nearby Lake Hayq and the historic Istifanos Monastery situated on an island in the lake.
E1333358 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: Hayq | Statement: [Wollo, hasCity, Hayq]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hayq
Context triple: [Wollo, hasCity, Hayq]
  • A. Haisyn
    Haisyn is a city in central Ukraine known as a local administrative and economic center within Vinnytsia Oblast.
  • B. Haykota
    Haykota is a town in Eritrea’s Gash-Barka region, known primarily as a local agricultural and administrative center.
  • C. Hain
    Hain is an ancient, central world in Ursula K. Le Guin’s Hainish Cycle, often portrayed as the cradle of human-like civilizations across the galaxy.
  • D. Hahyah
    Hahyah is a figure from the apocryphal Book of Giants, traditionally portrayed as one of the giant offspring of fallen angels whose violent deeds contribute to the narrative of divine judgment.
  • E. Khayishan
    Khayishan, better known by his temple name Külüg Khan, was a Yuan dynasty emperor of Mongol China in the early 14th century.
  • 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: Hayq
Triple: [Wollo, hasCity, Hayq]
Generated description
Hayq is a town in Ethiopia’s Amhara Region, known for its nearby Lake Hayq and the historic Istifanos Monastery situated on an island in the lake.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hayq
Target entity description: Hayq is a town in Ethiopia’s Amhara Region, known for its nearby Lake Hayq and the historic Istifanos Monastery situated on an island in the lake.
  • A. Haisyn
    Haisyn is a city in central Ukraine known as a local administrative and economic center within Vinnytsia Oblast.
  • B. Haykota
    Haykota is a town in Eritrea’s Gash-Barka region, known primarily as a local agricultural and administrative center.
  • C. Hain
    Hain is an ancient, central world in Ursula K. Le Guin’s Hainish Cycle, often portrayed as the cradle of human-like civilizations across the galaxy.
  • D. Hahyah
    Hahyah is a figure from the apocryphal Book of Giants, traditionally portrayed as one of the giant offspring of fallen angels whose violent deeds contribute to the narrative of divine judgment.
  • E. Khayishan
    Khayishan, better known by his temple name Külüg Khan, was a Yuan dynasty emperor of Mongol China in the early 14th century.
  • 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_69d8d38bbe7c8190bdec3138e7d413c9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54d07dc288190bb3b8b5ab06518da completed April 19, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050390bd4c8190b623f08a12eee39b completed May 13, 2026, 11:04 p.m.
NEDg Description generation batch_6a050455e6e8819084927b1c2d4a5237 completed May 13, 2026, 11:08 p.m.
NED2 Entity disambiguation (via description) batch_6a0505cbc11481908e61d90dd64f6212 completed May 13, 2026, 11:14 p.m.
Created at: April 10, 2026, 11:46 a.m.