Triple

T16259921
Position Surface form Disambiguated ID Type / Status
Subject Sipiso-piso Waterfall E394726 entity
Predicate locatedNear P294 FINISHED
Object Tongging
Tongging is a village in North Sumatra, Indonesia, known as a scenic gateway to Lake Toba and the nearby Sipiso-piso Waterfall.
E1201703 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: Tongging | Statement: [Sipiso-piso Waterfall, locatedNear, Tongging]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tongging
Context triple: [Sipiso-piso Waterfall, locatedNear, Tongging]
  • A. Dayong
    Dayong is the former name of the city now known as Zhangjiajie in Hunan Province, China, famed for its dramatic sandstone pillar landscapes.
  • B. Tangtse
    Tangtse is a village in the Leh district of Ladakh, India, situated along key routes between the Indus Valley and the Pangong Tso region in the Himalayas.
  • C. Guting
    Guting is a key Taipei Metro station in central Taipei that serves as a transfer point between multiple subway lines.
  • D. Bingchang
    Bingchang is a Chinese given name, notably borne by diplomat and politician Fu Bingchang.
  • E. Chinju
    Chinju (often spelled Jinju) is a city in South Gyeongsang Province, South Korea, known for its historic fortress, Namgang Yudeung (Lantern) Festival, and rich cultural heritage.
  • 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: Tongging
Triple: [Sipiso-piso Waterfall, locatedNear, Tongging]
Generated description
Tongging is a village in North Sumatra, Indonesia, known as a scenic gateway to Lake Toba and the nearby Sipiso-piso Waterfall.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tongging
Target entity description: Tongging is a village in North Sumatra, Indonesia, known as a scenic gateway to Lake Toba and the nearby Sipiso-piso Waterfall.
  • A. Dayong
    Dayong is the former name of the city now known as Zhangjiajie in Hunan Province, China, famed for its dramatic sandstone pillar landscapes.
  • B. Tangtse
    Tangtse is a village in the Leh district of Ladakh, India, situated along key routes between the Indus Valley and the Pangong Tso region in the Himalayas.
  • C. Guting
    Guting is a key Taipei Metro station in central Taipei that serves as a transfer point between multiple subway lines.
  • D. Bingchang
    Bingchang is a Chinese given name, notably borne by diplomat and politician Fu Bingchang.
  • E. Chinju
    Chinju (often spelled Jinju) is a city in South Gyeongsang Province, South Korea, known for its historic fortress, Namgang Yudeung (Lantern) Festival, and rich cultural heritage.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245c3082c8190a1c9f92b255fdbb6 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000eee110c819088d99b80435ab70b completed May 10, 2026, 4:51 a.m.
NEDg Description generation batch_6a000f7e6338819099598bc22d31cd22 completed May 10, 2026, 4:54 a.m.
NED2 Entity disambiguation (via description) batch_6a001025300c819084933d9c6d19fe97 completed May 10, 2026, 4:57 a.m.
Created at: April 10, 2026, 5:04 a.m.