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.