Triple

T15767899
Position Surface form Disambiguated ID Type / Status
Subject Curzon family E382272 entity
Predicate hasTitle P38 FINISHED
Object Earl Howe E276499 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: Earl Howe | Statement: [Curzon family, hasTitle, Earl Howe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Earl Howe
Context triple: [Curzon family, hasTitle, Earl Howe]
  • A. Earl Howe chosen
    Earl Howe is a British Conservative politician and hereditary peer who has held several senior defence and health roles in the UK government.
  • B. Donald Ross
    Donald Ross was the first husband of legendary American singer, pianist, and civil rights activist Nina Simone.
  • C. Donald Ross
    Donald Ross was a prominent early 20th-century golf course architect renowned for designing many classic courses across the United States.
  • D. Harvey Penick
    Harvey Penick was a renowned American golf coach and author best known for his influential instructional book "Harvey Penick's Little Red Book."
  • E. Tom Morris Jr.
    Tom Morris Jr. is an American television personality and crime reporter best known as the co-host and field correspondent on the law-enforcement reality series "Live PD."
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e051951bac8190a7d45f3612c6de72 completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff877a67008190b05f879d05876fd3 completed May 9, 2026, 7:14 p.m.
Created at: April 10, 2026, 4:47 a.m.