Triple

T19198736
Position Surface form Disambiguated ID Type / Status
Subject Dave Guard E470042 entity
Predicate familyName P18 FINISHED
Object Guard 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: Guard | Statement: [Dave Guard, familyName, Guard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guard
Context triple: [Dave Guard, familyName, Guard]
  • A. Guard chosen
    Guard is a surname most notably borne by English actor Dominic Guard, known for his work in film, television, and theatre.
  • B. Guardea
    Guardea is a small Italian town and comune in the Umbria region, known for its medieval historic center and scenic position overlooking the Tiber Valley.
  • C. Main Guard
    Main Guard is a historic 17th-century courthouse and former civic building located in the center of Clonmel, County Tipperary, Ireland.
  • D. Gary
    Gary is a small town in McDowell County, West Virginia, historically known as a coal mining community.
  • E. Gary
    Gary is a masculine given name of English origin commonly used in the United States and other English-speaking countries.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a8daac8190b3558a1388596fb0 completed April 20, 2026, 9:58 a.m.
Created at: April 10, 2026, 12:07 p.m.