Triple

T18066170
Position Surface form Disambiguated ID Type / Status
Subject Coosan languages E432298 entity
Predicate glottologName P6521 FINISHED
Object Coosan NE NERFINISHED

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: Coosan | Statement: [Coosan languages, glottologName, Coosan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coosan
Context triple: [Coosan languages, glottologName, Coosan]
  • A. Coosan chosen
    Coosan is a small family of Native American languages traditionally spoken along the southern Oregon coast by the Coos peoples.
  • B. Miluk Coos
    Miluk Coos is a subgroup of the Coos people, an Indigenous community traditionally inhabiting the southern Oregon coast.
  • C. Barasana
    Barasana is an indigenous Tucanoan language spoken by the Barasana people of the northwest Amazon region, primarily in Colombia.
  • D. Qualicum
    Qualicum is a residential neighbourhood in the former city of Nepean, now part of Ottawa, Ontario, known for its suburban character and proximity to parks and schools.
  • E. Coëtquidan
    Coëtquidan is a military area in Brittany, France, best known as the site of the prestigious École spéciale militaire de Saint-Cyr officer training academy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4cce97ce08190a2f8762ce545e091 completed April 19, 2026, 12:39 p.m.
Created at: April 10, 2026, 10:26 a.m.