Triple

T15642725
Position Surface form Disambiguated ID Type / Status
Subject Bitou Cape E376105 entity
Predicate localName P657 FINISHED
Object 鼻頭角
鼻頭角 is a scenic coastal cape in northeastern Taiwan known for its dramatic sea cliffs, hiking trails, and panoramic ocean views.
 E1168178 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: 鼻頭角 | Statement: [Bitou Cape, localName, 鼻頭角]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 鼻頭角
Context triple: [Bitou Cape, localName, 鼻頭角]
  • A. Virchow's angle
    Virchow's angle is an anatomical measurement used in fetal ultrasound to assess cranial and facial development, named after the German pathologist Rudolf Virchow.
  • B. Eklizi-Burun
    Eklizi-Burun is a prominent mountain peak in Crimea, known as the summit of the Chatyr-Dag massif and a popular destination for hikers and nature enthusiasts.
  • C. Nose
    Nose is a city in Osaka Prefecture, Japan, known for its rural landscapes, historic temples, and traditional countryside atmosphere.
  • D. the Nose
    The Nose is the absurd, anthropomorphized facial feature that becomes an independent character in Nikolai Gogol’s satirical short story of the same name.
  • E. Lefort
    Lefort is a surname most notably associated with Franz Lefort, a 17th-century Genevan-born military officer and close advisor to Russian Tsar Peter the Great.
  • 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: 鼻頭角
Triple: [Bitou Cape, localName, 鼻頭角]
Generated description
鼻頭角 is a scenic coastal cape in northeastern Taiwan known for its dramatic sea cliffs, hiking trails, and panoramic ocean views.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 鼻頭角
Target entity description: 鼻頭角 is a scenic coastal cape in northeastern Taiwan known for its dramatic sea cliffs, hiking trails, and panoramic ocean views.
  • A. Virchow's angle
    Virchow's angle is an anatomical measurement used in fetal ultrasound to assess cranial and facial development, named after the German pathologist Rudolf Virchow.
  • B. Eklizi-Burun
    Eklizi-Burun is a prominent mountain peak in Crimea, known as the summit of the Chatyr-Dag massif and a popular destination for hikers and nature enthusiasts.
  • C. Nose
    Nose is a city in Osaka Prefecture, Japan, known for its rural landscapes, historic temples, and traditional countryside atmosphere.
  • D. the Nose
    The Nose is the absurd, anthropomorphized facial feature that becomes an independent character in Nikolai Gogol’s satirical short story of the same name.
  • E. Lefort
    Lefort is a surname most notably associated with Franz Lefort, a 17th-century Genevan-born military officer and close advisor to Russian Tsar Peter the Great.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ed23d688190bea996f90989d406 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f4d49188190855a895c5844dee0 completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff614906cc81909d978d8645045af3 completed May 9, 2026, 4:31 p.m.
NED2 Entity disambiguation (via description) batch_69ff61b3b3f08190a2a1e1010684a316 completed May 9, 2026, 4:32 p.m.
Created at: April 10, 2026, 4:15 a.m.