Triple

T14612982
Position Surface form Disambiguated ID Type / Status
Subject Akkar Governorate E343005 entity
Predicate hasCity P316 FINISHED
Object Berqayel
Berqayel is a town located in northern Lebanon within the Akkar region, known for its rural character and agricultural surroundings.
E1111262 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: Berqayel | Statement: [Akkar Governorate, hasCity, Berqayel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berqayel
Context triple: [Akkar Governorate, hasCity, Berqayel]
  • A. Kerebe
    Kerebe is a Bantu language spoken by the Kerewe people, primarily on Ukerewe Island in Lake Victoria, Tanzania.
  • B. Yonas
    Yonas is a given name, often used as a variant of Jonas in various cultures.
  • C. Biram
    Biram is an ancient Hausa city in northern Nigeria traditionally regarded as one of the original Hausa city-states (Hausa Bakwai) and an early center of Hausa culture and authority.
  • D. Semaq Beri
    Semaq Beri is an Aslian language spoken by an indigenous Orang Asli community in Peninsular Malaysia.
  • E. Gädl of Saint Lalibela
    The Gädl of Saint Lalibela is a medieval Ethiopian hagiographic text recounting the life, miracles, and sanctity of King Lalibela, famed for commissioning the rock-hewn churches of Lalibela.
  • 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: Berqayel
Triple: [Akkar Governorate, hasCity, Berqayel]
Generated description
Berqayel is a town located in northern Lebanon within the Akkar region, known for its rural character and agricultural surroundings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Berqayel
Target entity description: Berqayel is a town located in northern Lebanon within the Akkar region, known for its rural character and agricultural surroundings.
  • A. Kerebe
    Kerebe is a Bantu language spoken by the Kerewe people, primarily on Ukerewe Island in Lake Victoria, Tanzania.
  • B. Yonas
    Yonas is a given name, often used as a variant of Jonas in various cultures.
  • C. Biram
    Biram is an ancient Hausa city in northern Nigeria traditionally regarded as one of the original Hausa city-states (Hausa Bakwai) and an early center of Hausa culture and authority.
  • D. Semaq Beri
    Semaq Beri is an Aslian language spoken by an indigenous Orang Asli community in Peninsular Malaysia.
  • E. Gädl of Saint Lalibela
    The Gädl of Saint Lalibela is a medieval Ethiopian hagiographic text recounting the life, miracles, and sanctity of King Lalibela, famed for commissioning the rock-hewn churches of Lalibela.
  • 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_69d822dec68081908c2553145c4051dc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb450e6588190a94488d8e71888c8 completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda92110e88190af47b713dd24520b completed May 8, 2026, 9:13 a.m.
NEDg Description generation batch_69fdb35a57f08190a2d3fe426185bc31 completed May 8, 2026, 9:56 a.m.
NED2 Entity disambiguation (via description) batch_69fdb400e08081908d0a782908ba5459 completed May 8, 2026, 9:59 a.m.
Created at: April 10, 2026, 1:25 a.m.