Triple

T18982475
Position Surface form Disambiguated ID Type / Status
Subject Bắc Ninh Province E464463 entity
Predicate hasTown P847 FINISHED
Object Từ Sơn
Từ Sơn is a town in northern Vietnam known for its traditional craft villages and proximity to Hanoi within Bắc Ninh Province.
 E1352304 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: Từ Sơn | Statement: [Bắc Ninh Province, hasTown, Từ Sơn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Từ Sơn
Context triple: [Bắc Ninh Province, hasTown, Từ Sơn]
  • A. Lương Sơn
    Lương Sơn is a township in northern Vietnam that serves as the administrative and economic center of Lương Sơn District in Hòa Bình Province.
  • B. Phúc Yên
    Phúc Yên is a city in northern Vietnam known for its proximity to Hanoi and its role as an industrial and transportation hub in the Red River Delta region.
  • C. Yên Lạc
    Yên Lạc is a township in northern Vietnam that serves as the administrative and economic center of Yên Lạc District in Vĩnh Phúc Province.
  • D. Chúc Sơn
    Chúc Sơn is a township in Hanoi, Vietnam, serving as an administrative and commercial center for the surrounding rural area.
  • E. Hòa Lạc
    Hòa Lạc is a commune in the outskirts of Hanoi, Vietnam, known as a major hub for science, technology, and high-tech development.
  • 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: Từ Sơn
Triple: [Bắc Ninh Province, hasTown, Từ Sơn]
Generated description
Từ Sơn is a town in northern Vietnam known for its traditional craft villages and proximity to Hanoi within Bắc Ninh Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Từ Sơn
Target entity description: Từ Sơn is a town in northern Vietnam known for its traditional craft villages and proximity to Hanoi within Bắc Ninh Province.
  • A. Lương Sơn
    Lương Sơn is a township in northern Vietnam that serves as the administrative and economic center of Lương Sơn District in Hòa Bình Province.
  • B. Phúc Yên
    Phúc Yên is a city in northern Vietnam known for its proximity to Hanoi and its role as an industrial and transportation hub in the Red River Delta region.
  • C. Yên Lạc
    Yên Lạc is a township in northern Vietnam that serves as the administrative and economic center of Yên Lạc District in Vĩnh Phúc Province.
  • D. Chúc Sơn
    Chúc Sơn is a township in Hanoi, Vietnam, serving as an administrative and commercial center for the surrounding rural area.
  • E. Hòa Lạc
    Hòa Lạc is a commune in the outskirts of Hanoi, Vietnam, known as a major hub for science, technology, and high-tech development.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d65d27548190b86d4c5f5b51d809 completed April 20, 2026, 7:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05ad43dbb88190a34ff757ca925cbf completed May 14, 2026, 11:08 a.m.
NEDg Description generation batch_6a05aedf05c4819096ac6a61ada4b310 completed May 14, 2026, 11:15 a.m.
NED2 Entity disambiguation (via description) batch_6a05afe523208190a97142cd8e3b887b completed May 14, 2026, 11:20 a.m.
Created at: April 10, 2026, 12:01 p.m.