Triple

T3991560
Position Surface form Disambiguated ID Type / Status
Subject Bulu language E87000 entity
Predicate hasDialect P4251 FINISHED
Object Yelinda
Yelinda is a dialect of the Bulu language spoken by a specific subgroup of Bulu speakers in Cameroon.
 E403730 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: Yelinda | Statement: [Bulu language, hasDialect, Yelinda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yelinda
Context triple: [Bulu language, hasDialect, Yelinda]
  • A. Alinda
    Alinda was an important ancient city in the region of Caria in southwestern Anatolia, known for its strategic location and well-preserved Hellenistic ruins.
  • B. Maiana
    Maiana is a low-lying coral atoll in the central Pacific nation of Kiribati, known for its traditional village life and vulnerability to sea-level rise.
  • C. Yanaon
    Yanaon is the former name of Yanam, a small coastal town in India that was once part of French India and retains a distinct Franco-Indian cultural heritage.
  • D. Lusiana
    Lusiana is a small town in the Veneto region of northern Italy, known as the birthplace of Indian politician Sonia Gandhi.
  • E. Yahi
    The Yahi were a small Native American group from northern California, known for being among the last surviving independent Indigenous peoples in the region and for the story of Ishi, their last known member.
  • 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: Yelinda
Triple: [Bulu language, hasDialect, Yelinda]
Generated description
Yelinda is a dialect of the Bulu language spoken by a specific subgroup of Bulu speakers in Cameroon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yelinda
Target entity description: Yelinda is a dialect of the Bulu language spoken by a specific subgroup of Bulu speakers in Cameroon.
  • A. Alinda
    Alinda was an important ancient city in the region of Caria in southwestern Anatolia, known for its strategic location and well-preserved Hellenistic ruins.
  • B. Maiana
    Maiana is a low-lying coral atoll in the central Pacific nation of Kiribati, known for its traditional village life and vulnerability to sea-level rise.
  • C. Yanaon
    Yanaon is the former name of Yanam, a small coastal town in India that was once part of French India and retains a distinct Franco-Indian cultural heritage.
  • D. Lusiana
    Lusiana is a small town in the Veneto region of northern Italy, known as the birthplace of Indian politician Sonia Gandhi.
  • E. Yahi
    The Yahi were a small Native American group from northern California, known for being among the last surviving independent Indigenous peoples in the region and for the story of Ishi, their last known member.
  • 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_69aed94118148190975e6aa4e554cde9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefa02ed6881908e31d342413fed26 completed March 9, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b54035e92c81909dc2be18719b062c completed March 14, 2026, 11:02 a.m.
NEDg Description generation batch_69b541c668188190b5579e113149ddf5 completed March 14, 2026, 11:08 a.m.
NED2 Entity disambiguation (via description) batch_69b54266cf908190848a51e20739441f completed March 14, 2026, 11:11 a.m.
Created at: March 9, 2026, 3:33 p.m.