Triple

T9517605
Position Surface form Disambiguated ID Type / Status
Subject Koura District E229563 entity
Predicate hasTown P847 FINISHED
Object Bterram
Bterram is a town located in the Koura District of the North Governorate in Lebanon, known for its traditional rural character and Mediterranean setting.
 E804414 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: Bterram | Statement: [Koura District, hasTown, Bterram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bterram
Context triple: [Koura District, hasTown, Bterram]
  • A. Berrylands
    Berrylands is a suburban residential area in the Royal Borough of Kingston upon Thames in southwest London, known for its green spaces and proximity to the Hogsmill River.
  • B. Battir
    Battir is a Palestinian village near Bethlehem renowned for its ancient terraced agriculture and irrigation system, recognized as a UNESCO World Heritage Site.
  • C. Teroenza
    Teroenza is a character in the Star Wars universe known for being one of the earlier owners of the iconic starship Millennium Falcon.
  • D. Barim
    Barim is an alternative name for Perim Island, a strategically located island in the Bab-el-Mandeb strait between the Red Sea and the Gulf of Aden.
  • E. Bastan
    Bastan is a family of turboprop aircraft engines developed by Turbomeca and used on several regional and military transport aircraft.
  • 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: Bterram
Triple: [Koura District, hasTown, Bterram]
Generated description
Bterram is a town located in the Koura District of the North Governorate in Lebanon, known for its traditional rural character and Mediterranean setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bterram
Target entity description: Bterram is a town located in the Koura District of the North Governorate in Lebanon, known for its traditional rural character and Mediterranean setting.
  • A. Berrylands
    Berrylands is a suburban residential area in the Royal Borough of Kingston upon Thames in southwest London, known for its green spaces and proximity to the Hogsmill River.
  • B. Battir
    Battir is a Palestinian village near Bethlehem renowned for its ancient terraced agriculture and irrigation system, recognized as a UNESCO World Heritage Site.
  • C. Teroenza
    Teroenza is a character in the Star Wars universe known for being one of the earlier owners of the iconic starship Millennium Falcon.
  • D. Barim
    Barim is an alternative name for Perim Island, a strategically located island in the Bab-el-Mandeb strait between the Red Sea and the Gulf of Aden.
  • E. Bastan
    Bastan is a family of turboprop aircraft engines developed by Turbomeca and used on several regional and military transport aircraft.
  • 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_69ca84777560819084cddd999badc1aa completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9880417c819097dde277988df36d completed April 1, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69d13a4aeb008190ae5d54367efe2722 completed April 4, 2026, 4:20 p.m.
NEDg Description generation batch_69d13c78d6108190ad2cab79070077a8 completed April 4, 2026, 4:29 p.m.
NED2 Entity disambiguation (via description) batch_69d13d2aac8c8190a00c8fe820baa732 completed April 4, 2026, 4:32 p.m.
Created at: March 30, 2026, 7:59 p.m.