Triple

T6334234
Position Surface form Disambiguated ID Type / Status
Subject Jarawan Bantu E142451 entity
Predicate hasMemberLanguage P7390 FINISHED
Object Bankal
Bankal is a Jarawan Bantu language spoken by a small ethnic community in Nigeria.
E586684 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: Bankal | Statement: [Jarawan Bantu, hasMemberLanguage, Bankal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bankal
Context triple: [Jarawan Bantu, hasMemberLanguage, Bankal]
  • A. Beobanka
    Beobanka was a Yugoslav commercial bank based in Serbia that operated during the socialist and post-socialist periods before being dissolved amid the country’s 1990s economic turmoil.
  • B. Big Bank
    Big Bank is a popular hip-hop track by rapper YG featuring 2 Chainz, Big Sean, and Nicki Minaj, known for its catchy hook and heavy club-oriented production.
  • C. Ballana
    Ballana is an important archaeological site in Lower Nubia known for its rich group of royal tumulus graves from the post-Meroitic period.
  • D. Baní
    Baní is a city in the Peravia Province of the Dominican Republic, known as an important agricultural and historical center in the southern region of the country.
  • E. Bankura
    Bankura is a town in eastern India known as the administrative headquarters of Bankura district and for its terracotta temples and traditional crafts.
  • 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: Bankal
Triple: [Jarawan Bantu, hasMemberLanguage, Bankal]
Generated description
Bankal is a Jarawan Bantu language spoken by a small ethnic community in Nigeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bankal
Target entity description: Bankal is a Jarawan Bantu language spoken by a small ethnic community in Nigeria.
  • A. Beobanka
    Beobanka was a Yugoslav commercial bank based in Serbia that operated during the socialist and post-socialist periods before being dissolved amid the country’s 1990s economic turmoil.
  • B. Big Bank
    Big Bank is a popular hip-hop track by rapper YG featuring 2 Chainz, Big Sean, and Nicki Minaj, known for its catchy hook and heavy club-oriented production.
  • C. Ballana
    Ballana is an important archaeological site in Lower Nubia known for its rich group of royal tumulus graves from the post-Meroitic period.
  • D. Baní
    Baní is a city in the Peravia Province of the Dominican Republic, known as an important agricultural and historical center in the southern region of the country.
  • E. Bankura
    Bankura is a town in eastern India known as the administrative headquarters of Bankura district and for its terracotta temples and traditional crafts.
  • 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06549084c8190b73fd94c9e0cb302 completed March 22, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c60424a5dc8190820970fce13776ac completed March 27, 2026, 4:14 a.m.
NEDg Description generation batch_69c60626724881908e6270c2d3652c16 completed March 27, 2026, 4:23 a.m.
NED2 Entity disambiguation (via description) batch_69c606bd2228819082fcb63493664927 completed March 27, 2026, 4:25 a.m.
Created at: March 22, 2026, 4:30 p.m.