Triple

T10675109
Position Surface form Disambiguated ID Type / Status
Subject Samuel Ashe E251595 entity
Predicate familyName P18 FINISHED
Object Ashe E393185 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: Ashe | Statement: [Samuel Ashe, familyName, Ashe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ashe
Context triple: [Samuel Ashe, familyName, Ashe]
  • A. Ashe chosen
    Ashe is a small village in Hampshire, England, known for its rural setting near the headwaters of the River Test.
  • B. Ashe Marson
    Ashe Marson is a fictional young man-about-town and amateur sleuth created by P. G. Wodehouse, best known as one of the central characters in the comic novel "Something Fresh."
  • C. Caitlyn
    Caitlyn is the given name of Caitlyn Jenner, the American television personality and former Olympic gold medal–winning decathlete.
  • D. Reinhardt
    Reinhardt is a German-language surname borne by numerous notable individuals across fields such as music, military history, and the arts.
  • E. Reinhardt
    Reinhardt is a supporting character in the 2002 vampire action film "Blade II," appearing as a member of the Bloodpack team that initially allies with Blade.
  • 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_69d6aa5b0d2881909584b20efc5877f0 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6fb935ca88190b1312d3d53902af5 completed April 9, 2026, 1:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d998bfc27c8190a9d3e77fbe544a6d completed April 11, 2026, 12:41 a.m.
Created at: April 8, 2026, 9:09 p.m.