Triple

T2689368
Position Surface form Disambiguated ID Type / Status
Subject Kate E57561 entity
Predicate relatedName P3889 FINISHED
Object Katie E62170 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: Katie | Statement: [Kate, relatedName, Katie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katie
Context triple: [Kate, relatedName, Katie]
  • A. Katie Lucas
    Katie Lucas is an American screenwriter and actress best known for her work on the animated series "Star Wars: The Clone Wars" and as the daughter of filmmaker George Lucas.
  • B. Kathryn chosen
    Kathryn is a feminine given name, commonly considered a variant spelling of Katherine/Catherine.
  • C. Kathy
    Kathy is the given name of Kathy Hochul, the 57th governor of New York and the first woman to hold that office.
  • D. Katie DeWitt
    Katie DeWitt is a person notable enough to be recognized as a prominent bearer of the De Witt surname.
  • E. Katie Irving
    Katie Irving is known primarily as the daughter of American theater director and producer Jules Irving.
  • 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_69ab4a5028388190a36f3baf1588309e completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd9f380d48190953529d23688a328 completed March 7, 2026, 7:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69afaf5e85bc81908ba1b1968cfa440a completed March 10, 2026, 5:42 a.m.
Created at: March 6, 2026, 9:54 p.m.