Triple

T21264641
Position Surface form Disambiguated ID Type / Status
Subject Ezra Stiles E524094 entity
Predicate familyName P18 FINISHED
Object Stiles 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: Stiles | Statement: [Ezra Stiles, familyName, Stiles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stiles
Context triple: [Ezra Stiles, familyName, Stiles]
  • A. Stiles Stilinski chosen
    Stiles Stilinski is a quick-witted, loyal, and resourceful human character from the TV series "Teen Wolf," known for being Scott McCall’s best friend and a key member of his supernatural circle.
  • B. Jonas Steele
    Jonas Steele is the central fictional protagonist of the Civil War–era television miniseries "The Blue and the Gray," around whom much of the story’s personal and historical drama revolves.
  • C. Tyler Gage
    Tyler Gage is the talented street dancer and protagonist from the original "Step Up" film, whose character and legacy carry over into "Step Up 2: The Streets."
  • D. Hayden Wilde
    Hayden Wilde is a New Zealand triathlete and Olympic medalist known for his strong performances on the World Triathlon circuit.
  • E. Xander Berkeley
    Xander Berkeley is an American character actor known for his versatile supporting roles in film and television, including appearances in projects like "Terminator 2: Judgment Day," "24," and numerous other genre films and series.
  • 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_69e0b5156d7881909bd4f83676590715 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e735ea74e0819099d724de95996c90 completed April 21, 2026, 8:31 a.m.
Created at: April 16, 2026, 4 p.m.