Triple

T15424555
Position Surface form Disambiguated ID Type / Status
Subject Max Dennison E369472 entity
Predicate parent P120 FINISHED
Object Dave Dennison E1159425 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: Dave Dennison | Statement: [Max Dennison, parent, Dave Dennison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dave Dennison
Context triple: [Max Dennison, parent, Dave Dennison]
  • A. Dave Dennison chosen
    Dave Dennison is a fictional character associated with Dani Dennison in the Hocus Pocus film universe, depicted as a member of her family.
  • B. David Denny
    David Denny was a 19th-century American pioneer and early settler of Seattle, Washington, who played a key role in the city's founding and development.
  • C. Tony Denison
    Tony Denison is an American actor best known for his role as Detective Andy Flynn on the crime dramas "The Closer" and its spin-off "Major Crimes."
  • D. Max Dennison
    Max Dennison is the skeptical teenage protagonist of the Halloween-themed fantasy film "Hocus Pocus," whose actions accidentally resurrect three witches in Salem.
  • E. David Denman
    David Denman is an American actor best known for his role as Roy Anderson on the U.S. version of "The Office" and for supporting performances in films and television series across comedy and drama.
  • 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_69d85a1849f48190bf898068b2806fae completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ec032548190840b558dde6057c7 completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00dbf2567c81909ab6054ade27afac completed May 10, 2026, 7:26 p.m.
Created at: April 10, 2026, 3:20 a.m.