Triple

T22738429
Position Surface form Disambiguated ID Type / Status
Subject Bamileke people E562337 entity
Predicate traditionalRulerTitle P10605 FINISHED
Object Fon
Fon is the hereditary monarch and spiritual leader of many traditional kingdoms in Cameroon’s Grassfields region, particularly among groups such as the Bamileke.
 E1552673 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: Fon | Statement: [Bamileke people, traditionalRulerTitle, Fon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fon
Context triple: [Bamileke people, traditionalRulerTitle, Fon]
  • A. Fon
    Fon is a major Gbe language of West Africa, primarily spoken by the Fon people in Benin and neighboring countries.
  • B. Funka
    Funka is a small village in northern Poland known for its scenic lakeside setting and recreational access to Lake Charzykowskie.
  • C. Funt
    Funt is a surname most notably associated with Allen Funt, the creator and host of the pioneering hidden-camera television show "Candid Camera."
  • D. Fung
    Fung is a common Cantonese romanization of the Chinese surname typically spelled "Feng" in Mandarin pinyin.
  • E. FUNO
    FUNO is the stock ticker symbol for Fibra Uno, one of Mexico’s largest real estate investment trusts (REITs) focused on commercial properties.
  • 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: Fon
Triple: [Bamileke people, traditionalRulerTitle, Fon]
Generated description
Fon is the hereditary monarch and spiritual leader of many traditional kingdoms in Cameroon’s Grassfields region, particularly among groups such as the Bamileke.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fon
Target entity description: Fon is the hereditary monarch and spiritual leader of many traditional kingdoms in Cameroon’s Grassfields region, particularly among groups such as the Bamileke.
  • A. Fon
    Fon is a major Gbe language of West Africa, primarily spoken by the Fon people in Benin and neighboring countries.
  • B. Funka
    Funka is a small village in northern Poland known for its scenic lakeside setting and recreational access to Lake Charzykowskie.
  • C. Funt
    Funt is a surname most notably associated with Allen Funt, the creator and host of the pioneering hidden-camera television show "Candid Camera."
  • D. Fung
    Fung is a common Cantonese romanization of the Chinese surname typically spelled "Feng" in Mandarin pinyin.
  • E. FUNO
    FUNO is the stock ticker symbol for Fibra Uno, one of Mexico’s largest real estate investment trusts (REITs) focused on commercial properties.
  • 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_69e245513a5c81908d5cb471b4fc429d completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17971751081909253984429c8d178 completed April 29, 2026, 3:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b8fce978c81908b83f84dc1357c91 completed May 18, 2026, 10:16 p.m.
NEDg Description generation batch_6a0b937b20008190817512be3d48df39 completed May 18, 2026, 10:32 p.m.
NED2 Entity disambiguation (via description) batch_6a0b946320e0819097ef9c4638595dff completed May 18, 2026, 10:36 p.m.
Created at: April 17, 2026, 3:22 p.m.