Triple

T11800932
Position Surface form Disambiguated ID Type / Status
Subject Frank Thornton E280622 entity
Predicate workedOn P3 FINISHED
Object Sykes E749450 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: Sykes | Statement: [Frank Thornton, workedOn, Sykes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sykes
Context triple: [Frank Thornton, workedOn, Sykes]
  • A. Sykes
    Sykes is an English surname of Old Norse origin, commonly associated with families from northern England.
  • B. Sykes chosen
    Sykes is a British television sitcom best known for starring comedian Eric Sykes in a series of domestic and comedic misadventures.
  • C. Moneague
    Moneague is a rural village in Jamaica known for its karst landscape, seasonal lake, and location along the main road through Saint Ann Parish.
  • D. Sametto James
    Sametto James is a music producer best known for her work with and connection to the legendary blues figure known as the Matriarch of the Blues.
  • E. Mosby
    Mosby is a surname most famously associated with John S. Mosby, a Confederate cavalry battalion commander and guerrilla leader during the American Civil War.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a5a4512c8190b7782e1dee053000 completed April 10, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69f13129fa608190b080dc27f8bd7803 completed April 28, 2026, 10:14 p.m.
Created at: April 8, 2026, 9:42 p.m.