Triple

T8798472
Position Surface form Disambiguated ID Type / Status
Subject Southern Min E209343 entity
Predicate hasRomanization P2508 FINISHED
Object POJ
POJ (Pe̍h-ōe-jī) is a Latin-based orthography widely used for writing the Southern Min (Hokkien) language, especially in Taiwan and Southeast Asia.
 E759802 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: POJ | Statement: [Southern Min, hasRomanization, POJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: POJ
Context triple: [Southern Min, hasRomanization, POJ]
  • A. PKSOI
    PKSOI is the U.S. Army’s center of excellence for developing concepts, doctrine, and best practices for peacekeeping and stability operations worldwide.
  • B. NOI
    NOI is a concise instructional text in the Gaudiya Vaishnava tradition that offers practical guidance on progressive spiritual life and devotion to Krishna.
  • C. UVa
    UVa is the commonly used abbreviation for the historic Spanish public institution the University of Valladolid.
  • D. PRDOJ
    PRDOJ is the principal government agency in Puerto Rico responsible for enforcing the law, representing the Commonwealth in legal matters, and overseeing criminal prosecutions.
  • E. OJ
    OJ is the post-nominal abbreviation used to denote membership in the Order of Jamaica, one of the country’s highest national honours.
  • 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: POJ
Triple: [Southern Min, hasRomanization, POJ]
Generated description
POJ (Pe̍h-ōe-jī) is a Latin-based orthography widely used for writing the Southern Min (Hokkien) language, especially in Taiwan and Southeast Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: POJ
Target entity description: POJ (Pe̍h-ōe-jī) is a Latin-based orthography widely used for writing the Southern Min (Hokkien) language, especially in Taiwan and Southeast Asia.
  • A. PKSOI
    PKSOI is the U.S. Army’s center of excellence for developing concepts, doctrine, and best practices for peacekeeping and stability operations worldwide.
  • B. NOI
    NOI is a concise instructional text in the Gaudiya Vaishnava tradition that offers practical guidance on progressive spiritual life and devotion to Krishna.
  • C. UVa
    UVa is the commonly used abbreviation for the historic Spanish public institution the University of Valladolid.
  • D. PRDOJ
    PRDOJ is the principal government agency in Puerto Rico responsible for enforcing the law, representing the Commonwealth in legal matters, and overseeing criminal prosecutions.
  • E. OJ
    OJ is the post-nominal abbreviation used to denote membership in the Order of Jamaica, one of the country’s highest national honours.
  • 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_69ca836240888190a62b262e56a69d2f completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fa50dd081908fa5e4ffa70342e2 completed March 31, 2026, 11:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf6f658f248190957eba821b07cc4f completed April 3, 2026, 7:42 a.m.
NEDg Description generation batch_69cf713a184c8190b1fa788fd3ba8304 completed April 3, 2026, 7:50 a.m.
NED2 Entity disambiguation (via description) batch_69cf71d3517c819088c930ed468c4e8e completed April 3, 2026, 7:52 a.m.
Created at: March 30, 2026, 6:44 p.m.