Triple

T9561555
Position Surface form Disambiguated ID Type / Status
Subject Shughni E230685 entity
Predicate hasDialect P4251 FINISHED
Object Sarikoli (sometimes classified separately) E228138 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: Sarikoli (sometimes classified separately) | Statement: [Shughni, hasDialect, Sarikoli (sometimes classified separately)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarikoli (sometimes classified separately)
Context triple: [Shughni, hasDialect, Sarikoli (sometimes classified separately)]
  • A. Sarikoli language
    The Sarikoli language is an Eastern Iranian Pamir language spoken primarily by the Tajik ethnic minority in China’s Xinjiang region.
  • B. Sarikoli chosen
    Sarikoli is an Eastern Iranian language spoken primarily by the Tajik ethnic community in the Tashkurgan region of Xinjiang, China.
  • C. Son Koli
    Son Koli is a subcaste of the Koli community in India, traditionally associated with fishing and coastal livelihoods, particularly in the western coastal regions such as Maharashtra.
  • D. Sivaraksa
    Sivaraksa is the surname of Sulak Sivaraksa, a prominent Thai social activist, intellectual, and proponent of engaged Buddhism.
  • E. Sarba
    Sarba is a locality in Lebanon that forms part of the coastal urban area around Jounieh and falls within the pastoral jurisdiction of the Maronite Catholic Eparchy of Joubbé, Sarba and Jounieh.
  • 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_69ca847e53a88190a60eed7e02257f10 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd994d31e08190b139f5ad10d8ea31 completed April 1, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69d152a014a48190925d52967e1fbffe completed April 4, 2026, 6:04 p.m.
Created at: March 30, 2026, 8:03 p.m.