Triple

T9592542
Position Surface form Disambiguated ID Type / Status
Subject Shepard E231450 entity
Predicate hasVariant P455 FINISHED
Object Sheppard E659136 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: Sheppard | Statement: [Shepard, hasVariant, Sheppard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sheppard
Context triple: [Shepard, hasVariant, Sheppard]
  • A. Sheppard chosen
    Sheppard is a surname most famously associated with Kate Sheppard, a leading figure in the New Zealand women's suffrage movement.
  • B. Sheed
    Sheed is the popular nickname of Rasheed Wallace, a former NBA All-Star forward known for his fiery competitiveness, three-point shooting, and key role in the Detroit Pistons’ 2004 championship.
  • C. Seacrest
    Seacrest is the surname of American media personality and television host Ryan Seacrest, best known for hosting "American Idol" and numerous radio and TV programs.
  • D. Glennie
    Glennie is a Scottish surname most notably borne by Dame Evelyn Glennie, the renowned virtuoso percussionist.
  • E. Yessie
    Yessie is a studio album by Canadian singer-songwriter Jessie Reyez that showcases her emotionally raw R&B and pop sound.
  • 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_69ca8482884481908eccdfdf64d6fbf7 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a11ec7081908dc580de2f369706 completed April 1, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69d161938e108190aea76d528f9208a2 completed April 4, 2026, 7:08 p.m.
Created at: March 30, 2026, 8:07 p.m.