Triple

T6377024
Position Surface form Disambiguated ID Type / Status
Subject Bevan E143491 entity
Predicate derivedFrom P909 FINISHED
Object ap Evan E126478 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: ap Evan | Statement: [Bevan, derivedFrom, ap Evan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ap Evan
Context triple: [Bevan, derivedFrom, ap Evan]
  • A. Evan chosen
    Evan is a masculine given name of Welsh origin meaning "the Lord is gracious," commonly used in English-speaking countries.
  • B. Evan Richards
    Evan Richards is an American actor best known for his role in the film "Down and Out in Beverly Hills" and various television appearances in the 1980s and 1990s.
  • C. Evans
    Evans is the surname of David Howell Evans, better known as The Edge, the guitarist of the Irish rock band U2.
  • D. Evan Shelby
    Evan Shelby was a colonial-era frontiersman and militia officer in the American South, best known as the father of Revolutionary War hero and Kentucky’s first governor, Isaac Shelby.
  • E. Evan Moore
    Evan Moore is an entrepreneur best known as one of the co-founders of the food delivery platform DoorDash.
  • 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_69c008d9f4348190ab598a2913259a1c completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0683d7af881908d66d5230e1bfcb6 completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62da390c081908690ec716aed8fea completed March 27, 2026, 7:11 a.m.
Created at: March 22, 2026, 4:33 p.m.