Triple

T1603711
Position Surface form Disambiguated ID Type / Status
Subject Hakka E34449 entity
Predicate hasAlternativeName P39 FINISHED
Object Kejia
Kejia is another name for the Hakka language, a Sinitic language spoken by the Hakka people across southern China and various overseas communities.
E181224 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: Kejia | Statement: [Hakka, hasAlternativeName, Kejia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kejia
Context triple: [Hakka, hasAlternativeName, Kejia]
  • A. Ijesha
    Ijesha are a subgroup of the Yoruba people known for their distinct dialect, cultural traditions, and historical presence in southwestern Nigeria.
  • B. Njuká
    Njuká is an alternative name for the Ndyuka language, a creole spoken primarily by the Ndyuka Maroon community in Suriname and French Guiana.
  • C. Mayo Kébbi
    Mayo Kébbi is a river in Central Africa that serves as a key waterway in Chad and Cameroon, contributing to the regional drainage system connected to the Benue River.
  • D. Ndowe
    Ndowe is a Bantu language spoken by the Ndowe people along the coastal region of Equatorial Guinea.
  • E. Kezia Aoko
    Kezia Aoko is the first wife of Barack Obama Sr. and the stepmother of former U.S. President Barack Obama.
  • 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: Kejia
Triple: [Hakka, hasAlternativeName, Kejia]
Generated description
Kejia is another name for the Hakka language, a Sinitic language spoken by the Hakka people across southern China and various overseas communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kejia
Target entity description: Kejia is another name for the Hakka language, a Sinitic language spoken by the Hakka people across southern China and various overseas communities.
  • A. Ijesha
    Ijesha are a subgroup of the Yoruba people known for their distinct dialect, cultural traditions, and historical presence in southwestern Nigeria.
  • B. Njuká
    Njuká is an alternative name for the Ndyuka language, a creole spoken primarily by the Ndyuka Maroon community in Suriname and French Guiana.
  • C. Mayo Kébbi
    Mayo Kébbi is a river in Central Africa that serves as a key waterway in Chad and Cameroon, contributing to the regional drainage system connected to the Benue River.
  • D. Ndowe
    Ndowe is a Bantu language spoken by the Ndowe people along the coastal region of Equatorial Guinea.
  • E. Kezia Aoko
    Kezia Aoko is the first wife of Barack Obama Sr. and the stepmother of former U.S. President Barack Obama.
  • 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_69a885fea6a481909fe83ba6441f1774 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9094f96ec819090286c21b3dfddd5 completed March 5, 2026, 4:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad46ae8ef08190acf018f1db4bfa7c completed March 8, 2026, 9:51 a.m.
NEDg Description generation batch_69ad4827c51c8190b07f4e07ba710c9d completed March 8, 2026, 9:57 a.m.
NED2 Entity disambiguation (via description) batch_69ad487f5ce08190a72efddc64bd496c completed March 8, 2026, 9:59 a.m.
Created at: March 4, 2026, 7:28 p.m.