Triple

T19429589
Position Surface form Disambiguated ID Type / Status
Subject Western Keres E486073 entity
Predicate isDistinctFrom P1612 FINISHED
Object Eastern Keres 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: Eastern Keres | Statement: [Western Keres, isDistinctFrom, Eastern Keres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eastern Keres
Context triple: [Western Keres, isDistinctFrom, Eastern Keres]
  • A. Eastern Keres chosen
    Eastern Keres is a Keresan Puebloan language traditionally spoken by Native American communities in central New Mexico.
  • B. Western Keres
    Western Keres is a Keresan Puebloan language spoken by the Keres people of western New Mexico.
  • C. Keteyian
    Keteyian is the surname of Armen Keteyian, an American television journalist and author known for his investigative sports reporting.
  • D. Kataiysk
    Kataiysk is a small town in southwestern Siberia, Russia, serving as a local administrative and economic center within Kurgan Oblast.
  • E. Kiserian
    Kiserian is a rapidly growing town in Kenya’s Kajiado County, situated just southwest of Nairobi and known as a residential and trading hub for the surrounding Maasai pastoral communities.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6321b78d08190b86cef7c60cbb61c completed April 20, 2026, 2:03 p.m.
Created at: April 10, 2026, 1:37 p.m.