Triple

T19672255
Position Surface form Disambiguated ID Type / Status
Subject Tompkins E472360 entity
Predicate variantOf P4680 FINISHED
Object Tomkins NE NERFINISHED

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: Tomkins | Statement: [Tompkins, variantOf, Tomkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tomkins
Context triple: [Tompkins, variantOf, Tomkins]
  • A. Tomkins chosen
    Tomkins is an English-language surname borne by various notable individuals across fields such as sports, politics, and the arts.
  • B. Wayman
    Wayman is a masculine given name of English origin that has been borne by various notable American figures, including politicians and academics.
  • C. Tildon
    Tildon is a less common variant of the given name Tilden, typically used as a masculine first name.
  • D. Kiffin
    Kiffin is the surname of Lane Kiffin, a prominent American football coach known for leading several major college and NFL teams.
  • E. Manning
    Manning is an English-language surname borne by numerous notable figures across politics, sports, literature, and other fields.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416d61008190af531c6d346d7da1 completed April 20, 2026, 3:08 p.m.
Created at: April 10, 2026, 1:45 p.m.