Triple

T3650535
Position Surface form Disambiguated ID Type / Status
Subject Keelung E77406 entity
Predicate alternativeName P39 FINISHED
Object Chilung
Chilung is an alternative romanization of Keelung, a major port city in northern Taiwan known for its harbor and night market.
 E376549 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: Chilung | Statement: [Keelung, alternativeName, Chilung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Chilung
Context triple: [Keelung, alternativeName, Chilung]
  • A. Chuping
    Chuping is a town in the Malaysian state of Perlis, known for its extensive sugarcane plantations and hot climate.
  • B. Chang La
    Chang La is a high-altitude mountain pass in the Indian Himalayas, known as one of the world’s highest motorable roads and a key route toward the Pangong Lake region in Ladakh.
  • C. 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.
  • D. Machang
    Machang is a town and administrative district in the Malaysian state of Kelantan, known for its semi-urban character and role as a local commercial and educational hub.
  • E. Langho
    Langho is a village in Lancashire, England, situated within the rural borough of Ribble Valley.
  • 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: Chilung
Triple: [Keelung, alternativeName, Chilung]
Generated description
Chilung is an alternative romanization of Keelung, a major port city in northern Taiwan known for its harbor and night market.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Chilung
Target entity description: Chilung is an alternative romanization of Keelung, a major port city in northern Taiwan known for its harbor and night market.
  • A. Chuping
    Chuping is a town in the Malaysian state of Perlis, known for its extensive sugarcane plantations and hot climate.
  • B. Chang La
    Chang La is a high-altitude mountain pass in the Indian Himalayas, known as one of the world’s highest motorable roads and a key route toward the Pangong Lake region in Ladakh.
  • C. 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.
  • D. Machang
    Machang is a town and administrative district in the Malaysian state of Kelantan, known for its semi-urban character and role as a local commercial and educational hub.
  • E. Langho
    Langho is a village in Lancashire, England, situated within the rural borough of Ribble Valley.
  • 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_69ad85def5cc8190863dccf55a18bebb completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc39303bc819090725643e53a96d6 completed March 8, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f4002948190af41072962006f51 completed March 13, 2026, 5:54 p.m.
NEDg Description generation batch_69b4531590408190b6048b6b0335eb0a completed March 13, 2026, 6:10 p.m.
NED2 Entity disambiguation (via description) batch_69b466719c788190a70d8338b45c28ab completed March 13, 2026, 7:33 p.m.
Created at: March 8, 2026, 3:24 p.m.