Triple

T15088548
Position Surface form Disambiguated ID Type / Status
Subject Stephen Dillane E360348 entity
Predicate hasRelative P367 FINISHED
Object Frank Dillane E640503 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: Frank Dillane | Statement: [Stephen Dillane, hasRelative, Frank Dillane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Dillane
Context triple: [Stephen Dillane, hasRelative, Frank Dillane]
  • A. Frank Dillane chosen
    Frank Dillane is an English actor best known for his role as Nick Clark in the television series "Fear the Walking Dead" and for playing young Tom Riddle in "Harry Potter and the Half-Blood Prince."
  • B. Stephen Dillane
    Stephen Dillane is a British actor known for his nuanced performances in film, television, and theatre, including roles in "Game of Thrones," "The Tunnel," and "The Hours."
  • C. Seamus Tierney
    Seamus Tierney is a cinematographer known for his work on the film "Love, Antosha."
  • D. Brian Connolly
    Brian Connolly was a Scottish singer best known as the lead vocalist of the 1970s glam rock band The Sweet.
  • E. Matt Hennessy
    Matt Hennessy is a computer scientist known for his contributions to the theory of concurrent and distributed systems, particularly in process algebra and semantics.
  • 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_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00277ea808190be3f002a8316eff1 completed April 15, 2026, 9:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0035428e608190b8bb41dabda044d1 completed May 10, 2026, 7:35 a.m.
Created at: April 10, 2026, 3:04 a.m.