Triple

T14788321
Position Surface form Disambiguated ID Type / Status
Subject Bajju E347585 entity
Predicate hasAutonym P1435 FINISHED
Object Bajju E347585 NE FINISHED

How this triple was built (2 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: Bajju | Statement: [Bajju, hasAutonym, Bajju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bajju
Context triple: [Bajju, hasAutonym, Bajju]
  • A. Bajju chosen
    Bajju are an ethnic subgroup in southern Kaduna State, Nigeria, closely related culturally and linguistically to the Atyap people.
  • B. Bajjika
    Bajjika is an Indo-Aryan language spoken primarily in parts of Bihar and Nepal, closely related to Maithili and considered one of the Bihari languages.
  • C. Bhokar
    Bhokar is a legislative assembly constituency in the Nanded district of Maharashtra, India.
  • D. Jubbarhatti
    Jubbarhatti is a small village in Himachal Pradesh, India, known primarily for hosting the airstrip that serves Shimla and its surrounding region.
  • E. Gajwel
    Gajwel is a prominent town in the Indian state of Telangana, known as an important regional center for administration, trade, and agriculture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decaa1e9ec81908d7c26c1c4e43014 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24b9e8a08190bc736ac207b77324 completed May 8, 2026, 6 p.m.
Created at: April 10, 2026, 1:31 a.m.