Triple

T4576428
Position Surface form Disambiguated ID Type / Status
Subject Taiwanese Hokkien E123149 entity
Predicate romanizationSystem P6517 FINISHED
Object Tailo
Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
 E453788 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: Tailo | Statement: [Taiwanese Hokkien, romanizationSystem, Tailo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tailo
Context triple: [Taiwanese Hokkien, romanizationSystem, Tailo]
  • A. Shompen
    The Shompen are an isolated indigenous people of Great Nicobar Island, known for their semi-nomadic forest-based lifestyle and limited contact with the outside world.
  • B. Vestini
    The Vestini were an ancient Italic tribe that inhabited the central Apennine region of Italy, particularly in what is now Abruzzo, during the pre-Roman and early Roman periods.
  • C. Cappa
    Cappa is the stage name and common nickname of Cappadonna, an American rapper closely associated with the Wu-Tang Clan.
  • D. Naiki
    Naiki is a Dravidian language spoken by indigenous communities in central India, particularly in parts of Maharashtra and adjoining regions.
  • E. Biskinik
    Biskinik is the official newspaper of the Choctaw Nation, providing news, cultural information, and community updates for Choctaw citizens.
  • 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: Tailo
Triple: [Taiwanese Hokkien, romanizationSystem, Tailo]
Generated description
Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tailo
Target entity description: Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
  • A. Shompen
    The Shompen are an isolated indigenous people of Great Nicobar Island, known for their semi-nomadic forest-based lifestyle and limited contact with the outside world.
  • B. Vestini
    The Vestini were an ancient Italic tribe that inhabited the central Apennine region of Italy, particularly in what is now Abruzzo, during the pre-Roman and early Roman periods.
  • C. Cappa
    Cappa is the stage name and common nickname of Cappadonna, an American rapper closely associated with the Wu-Tang Clan.
  • D. Naiki
    Naiki is a Dravidian language spoken by indigenous communities in central India, particularly in parts of Maharashtra and adjoining regions.
  • E. Biskinik
    Biskinik is the official newspaper of the Choctaw Nation, providing news, cultural information, and community updates for Choctaw citizens.
  • 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_69bd46466c7081909d07f36be2d08804 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd58dfe3508190b21836079e951a3c completed March 20, 2026, 2:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdd3e656a08190bb48d2ecae1eb798 completed March 20, 2026, 11:10 p.m.
NEDg Description generation batch_69bdd71b55d8819085340c8abb9c369e completed March 20, 2026, 11:24 p.m.
NED2 Entity disambiguation (via description) batch_69bdd78c9a008190b774db2742a3b371 completed March 20, 2026, 11:26 p.m.
Created at: March 20, 2026, 1:10 p.m.