Triple

T3165452
Position Surface form Disambiguated ID Type / Status
Subject Wu E66200 entity
Predicate hasVariantSpelling P457 FINISHED
Object Goh
Goh is a surname and given name commonly found in East and Southeast Asia, often representing a romanization of several different Chinese surnames.
 E333484 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: Goh | Statement: [Wu, hasVariantSpelling, Goh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Goh
Context triple: [Wu, hasVariantSpelling, Goh]
  • A. Gongman
    Gongman is the iconic figure who strikes a large gong in the opening logo sequence of the Rank Organisation’s films.
  • B. Goemai
    Goemai is a West Chadic language spoken primarily in central Nigeria by the Goemai people.
  • C. Garai
    Garai is a surname most notably associated with English actress and director Romola Garai.
  • D. Oghi
    Oghi is a town in Pakistan's Khyber Pakhtunkhwa province, known as a local administrative and commercial center within the Hazara region.
  • E. Joyo
    Joyo is a small city in Japan known for its location in Kyoto Prefecture and its blend of residential areas, light industry, and historical sites.
  • 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: Goh
Triple: [Wu, hasVariantSpelling, Goh]
Generated description
Goh is a surname and given name commonly found in East and Southeast Asia, often representing a romanization of several different Chinese surnames.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Goh
Target entity description: Goh is a surname and given name commonly found in East and Southeast Asia, often representing a romanization of several different Chinese surnames.
  • A. Gongman
    Gongman is the iconic figure who strikes a large gong in the opening logo sequence of the Rank Organisation’s films.
  • B. Goemai
    Goemai is a West Chadic language spoken primarily in central Nigeria by the Goemai people.
  • C. Garai
    Garai is a surname most notably associated with English actress and director Romola Garai.
  • D. Oghi
    Oghi is a town in Pakistan's Khyber Pakhtunkhwa province, known as a local administrative and commercial center within the Hazara region.
  • E. Joyo
    Joyo is a small city in Japan known for its location in Kyoto Prefecture and its blend of residential areas, light industry, and historical sites.
  • 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_69ad8585d7988190af37365331093ccd completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6424ee48190a29891ffbbc3811d completed March 8, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b235dca2848190bc2a46d6dd1c9fc7 completed March 12, 2026, 3:41 a.m.
NEDg Description generation batch_69b236e4efe08190ade7c1cc4b941639 completed March 12, 2026, 3:45 a.m.
NED2 Entity disambiguation (via description) batch_69b2375a75488190b3f2215c85d43f9c completed March 12, 2026, 3:47 a.m.
Created at: March 8, 2026, 3:06 p.m.