Triple

T15958596
Position Surface form Disambiguated ID Type / Status
Subject Taft Jordan E386999 entity
Predicate givenName P17 FINISHED
Object Taft E483155 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: Taft | Statement: [Taft Jordan, givenName, Taft]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taft
Context triple: [Taft Jordan, givenName, Taft]
  • A. Taft chosen
    Taft is a prominent American family name most famously associated with U.S. President and Chief Justice William Howard Taft and his politically influential relatives.
  • B. Taft
    Taft is a small oil-producing city in southwestern Kern County, California, known historically for its role in the petroleum industry.
  • C. Taft
    Taft is a small city in central Iran known for its traditional gardens, pomegranate orchards, and proximity to the historic desert city of Yazd.
  • D. Taft
    Taft is a coastal municipality in the province of Eastern Samar in the Philippines.
  • E. Taft
    Taft is a small town in Muskogee County, Oklahoma, historically known as one of the state's all-Black communities.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156fd7ce08190b5db4b486ccb6e40 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf16b1b881909768d18b889260da completed May 10, 2026, 12:19 a.m.
Created at: April 10, 2026, 4:53 a.m.