Triple

T12389465
Position Surface form Disambiguated ID Type / Status
Subject Western Desert language E295953 entity
Predicate hasDialect P4251 FINISHED
Object Manyjilyjarra
Manyjilyjarra is an Australian Aboriginal language variety spoken by Indigenous communities in the Western Desert region of Western Australia.
 E982331 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: Manyjilyjarra | Statement: [Western Desert language, hasDialect, Manyjilyjarra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Manyjilyjarra
Context triple: [Western Desert language, hasDialect, Manyjilyjarra]
  • A. Marajil
    Marajil was the mother of the Abbasid caliph al-Ma'mun and a woman of the early ninth-century Abbasid court.
  • B. Muyil
    Muyil is an ancient Maya archaeological site in Mexico’s Yucatán Peninsula, known for its well-preserved temples and proximity to the Sian Ka'an Biosphere Reserve.
  • C. Marau
    Marau is an Oceanic language spoken by a small community in Papua New Guinea.
  • D. Miasino
    Miasino is a small Italian town in the Piedmont region, known for its scenic location near Lake Orta and its historic villas and churches.
  • E. Nyishi
    The Nyishi are one of the major indigenous tribes of northeastern India, known for their distinct language, traditional bamboo and cane craftsmanship, and rich cultural heritage.
  • 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: Manyjilyjarra
Triple: [Western Desert language, hasDialect, Manyjilyjarra]
Generated description
Manyjilyjarra is an Australian Aboriginal language variety spoken by Indigenous communities in the Western Desert region of Western Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Manyjilyjarra
Target entity description: Manyjilyjarra is an Australian Aboriginal language variety spoken by Indigenous communities in the Western Desert region of Western Australia.
  • A. Marajil
    Marajil was the mother of the Abbasid caliph al-Ma'mun and a woman of the early ninth-century Abbasid court.
  • B. Muyil
    Muyil is an ancient Maya archaeological site in Mexico’s Yucatán Peninsula, known for its well-preserved temples and proximity to the Sian Ka'an Biosphere Reserve.
  • C. Marau
    Marau is an Oceanic language spoken by a small community in Papua New Guinea.
  • D. Miasino
    Miasino is a small Italian town in the Piedmont region, known for its scenic location near Lake Orta and its historic villas and churches.
  • E. Nyishi
    The Nyishi are one of the major indigenous tribes of northeastern India, known for their distinct language, traditional bamboo and cane craftsmanship, and rich cultural heritage.
  • 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fcf6aa8819080c9a2407a72db2e completed April 10, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63479df38819085c5ca791c460d5e completed May 2, 2026, 5:29 p.m.
NEDg Description generation batch_69f6389115e48190b5b556635930b0d9 completed May 2, 2026, 5:46 p.m.
NED2 Entity disambiguation (via description) batch_69f6397a3458819095b94ae7f9d5f106 completed May 2, 2026, 5:50 p.m.
Created at: April 8, 2026, 9:54 p.m.