Triple

T15253014
Position Surface form Disambiguated ID Type / Status
Subject Ellis County, Oklahoma E364565 entity
Predicate containsSettlement P847 FINISHED
Object May, Oklahoma E850771 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: May, Oklahoma | Statement: [Ellis County, Oklahoma, containsSettlement, May, Oklahoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: May, Oklahoma
Context triple: [Ellis County, Oklahoma, containsSettlement, May, Oklahoma]
  • A. May, Oklahoma chosen
    May, Oklahoma is a small rural town located in northwestern Oklahoma within Harper County.
  • B. Avant, Oklahoma
    Avant, Oklahoma is a small rural town located in northeastern Oklahoma within Osage County.
  • C. Ada, Oklahoma
    Ada, Oklahoma is a small city in south-central Oklahoma that serves as a regional economic and cultural hub and is notably home to the headquarters of the Chickasaw Nation.
  • D. Moore, Oklahoma
    Moore, Oklahoma is a suburban city in the Oklahoma City metropolitan area known for its rapid growth and history of devastating tornadoes.
  • E. Okarche, Oklahoma
    Okarche, Oklahoma is a small town in central Oklahoma known for its German-Catholic heritage and popular fried chicken restaurants.
  • 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_69d85a0dde7481908fc64d1e82d5d20d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e007f728648190b2c86e4528542b65 completed April 15, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fee5f572348190bd7719805e257e03 completed May 9, 2026, 7:44 a.m.
Created at: April 10, 2026, 3:13 a.m.