Triple

T8889113
Position Surface form Disambiguated ID Type / Status
Subject Mary Power E211616 entity
Predicate hasSurname P18 FINISHED
Object Power E774229 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: Power | Statement: [Mary Power, hasSurname, Power]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Power
Context triple: [Mary Power, hasSurname, Power]
  • A. Power
    "Power" is a critically acclaimed hip-hop song by Kanye West known for its bombastic production, introspective lyrics, and prominent use of progressive rock and soul samples.
  • B. Power chosen
    Power is an Irish surname historically associated with prominent political and landowning families, particularly in County Waterford and surrounding regions.
  • C. Power
    Power is a popular American crime drama television series that follows a New York City nightclub owner leading a double life as a drug kingpin.
  • D. Power
    "Power" is a contemporary classical composition by American composer John Stevens, known for its bold, energetic writing and prominent use of brass.
  • E. Power
    "Power" is an ecofeminist novel by Linda Hogan that explores the intertwined struggles of an Indigenous girl, her community, and the natural world in the face of environmental and cultural destruction.
  • 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_69ca83907954819096d52a245b635841 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc618f94108190b03248832bfe68a9 completed April 1, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0c6b99a3c8190b873b1cc94609ed6 completed April 4, 2026, 8:07 a.m.
Created at: March 30, 2026, 6:53 p.m.