Triple

T13087498
Position Surface form Disambiguated ID Type / Status
Subject North District E310374 entity
Predicate contains P35 FINISHED
Object Man Kam To
Man Kam To is a border area and control point in Hong Kong near the boundary with mainland China.
E1021205 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: Man Kam To | Statement: [North District, contains, Man Kam To]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Man Kam To
Context triple: [North District, contains, Man Kam To]
  • A. Fagamalo
    Fagamalo is a coastal village on the island of Savaiʻi in Samoa, known for its traditional Samoan lifestyle and scenic surroundings.
  • B. Hikong Ukol
    Hikong Ukol is one of the seven scenic waterfalls in Lake Sebu, South Cotabato, Philippines, known for its lush surroundings and cultural significance to the T'boli people.
  • C. Katete
    Katete is a town in eastern Zambia that serves as a key trading and transit hub near the border with Mozambique.
  • D. Kamaitachi
    Kamaitachi is the former ring name of professional wrestler Brice Morrow, used during his career in Japanese promotions.
  • E. To Kwa Wan
    To Kwa Wan is a residential and industrial neighborhood in Kowloon, Hong Kong, known for its older urban fabric, harborfront location, and ongoing redevelopment.
  • 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: Man Kam To
Triple: [North District, contains, Man Kam To]
Generated description
Man Kam To is a border area and control point in Hong Kong near the boundary with mainland China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Man Kam To
Target entity description: Man Kam To is a border area and control point in Hong Kong near the boundary with mainland China.
  • A. Fagamalo
    Fagamalo is a coastal village on the island of Savaiʻi in Samoa, known for its traditional Samoan lifestyle and scenic surroundings.
  • B. Hikong Ukol
    Hikong Ukol is one of the seven scenic waterfalls in Lake Sebu, South Cotabato, Philippines, known for its lush surroundings and cultural significance to the T'boli people.
  • C. Katete
    Katete is a town in eastern Zambia that serves as a key trading and transit hub near the border with Mozambique.
  • D. Kamaitachi
    Kamaitachi is the former ring name of professional wrestler Brice Morrow, used during his career in Japanese promotions.
  • E. To Kwa Wan
    To Kwa Wan is a residential and industrial neighborhood in Kowloon, Hong Kong, known for its older urban fabric, harborfront location, and ongoing redevelopment.
  • 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d981378dd08190b4f00e4e5df0e480 completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d614704481908758cf8691a941ea completed May 3, 2026, 4:59 a.m.
NEDg Description generation batch_69f6db8b74e08190919245104ac7ebd9 completed May 3, 2026, 5:22 a.m.
NED2 Entity disambiguation (via description) batch_69f6dc4db1e0819082f1b7e196e7f0c0 completed May 3, 2026, 5:25 a.m.
Created at: April 9, 2026, 9:02 p.m.