Triple

T14628037
Position Surface form Disambiguated ID Type / Status
Subject Neihu District E343403 entity
Predicate hasRomanization P2508 FINISHED
Object Neihu
Neihu is a district in northeastern Taipei, Taiwan, known for its technology parks, residential neighborhoods, and scenic lakeside and hillside areas.
E1110969 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: Neihu | Statement: [Neihu District, hasRomanization, Neihu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Neihu
Context triple: [Neihu District, hasRomanization, Neihu]
  • A. Niefang
    Niefang is a town in Equatorial Guinea located in the mainland province of Centro Sur.
  • B. Bocheng
    Bocheng is a Chinese given name most notably borne by the prominent Communist military leader and strategist Liu Bocheng.
  • C. Huili
    Huili was a Buddhist monk traditionally credited with establishing the renowned Lingyin Temple in Hangzhou, China.
  • D. Heqing
    Heqing was an era name used during the Northern Qi dynasty in imperial China to designate a specific reign period.
  • E. Dunhua
    Dunhua is a county-level city in northeastern China's Jilin Province, known for its location within the Yanbian Korean Autonomous Prefecture and its mix of Han and Korean cultural influences.
  • 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: Neihu
Triple: [Neihu District, hasRomanization, Neihu]
Generated description
Neihu is a district in northeastern Taipei, Taiwan, known for its technology parks, residential neighborhoods, and scenic lakeside and hillside areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Neihu
Target entity description: Neihu is a district in northeastern Taipei, Taiwan, known for its technology parks, residential neighborhoods, and scenic lakeside and hillside areas.
  • A. Niefang
    Niefang is a town in Equatorial Guinea located in the mainland province of Centro Sur.
  • B. Bocheng
    Bocheng is a Chinese given name most notably borne by the prominent Communist military leader and strategist Liu Bocheng.
  • C. Huili
    Huili was a Buddhist monk traditionally credited with establishing the renowned Lingyin Temple in Hangzhou, China.
  • D. Heqing
    Heqing was an era name used during the Northern Qi dynasty in imperial China to designate a specific reign period.
  • E. Dunhua
    Dunhua is a county-level city in northeastern China's Jilin Province, known for its location within the Yanbian Korean Autonomous Prefecture and its mix of Han and Korean cultural influences.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a7c8fc81909d10c1f563d7d1e7 completed April 14, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda92c25ac8190ba931c009e7ace19 completed May 8, 2026, 9:13 a.m.
NEDg Description generation batch_69fdb7e5aa6481908d4933e3932c5d03 completed May 8, 2026, 10:16 a.m.
NED2 Entity disambiguation (via description) batch_69fdb841f3a88190867c635950a1492c completed May 8, 2026, 10:17 a.m.
Created at: April 10, 2026, 1:26 a.m.