Triple

T5183228
Position Surface form Disambiguated ID Type / Status
Subject Harry Potter and the Prisoner of Azkaban (film) E116968 entity
Predicate starring P1507 FINISHED
Object Tom Felton E118209 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: Tom Felton | Statement: [Harry Potter and the Prisoner of Azkaban (film), starring, Tom Felton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Felton
Context triple: [Harry Potter and the Prisoner of Azkaban (film), starring, Tom Felton]
  • A. Tom Felton chosen
    Tom Felton is an English actor best known for playing Draco Malfoy in the Harry Potter film series.
  • B. Rupert Grint
    Rupert Grint is an English actor best known for playing Ron Weasley in the Harry Potter film series.
  • C. Nicholas Brendon
    Nicholas Brendon is an American actor best known for playing Xander Harris on the television series "Buffy the Vampire Slayer."
  • D. Daniel Radcliffe
    Daniel Radcliffe is an English actor best known for playing the title role in the Harry Potter film series.
  • E. Liam Aiken
    Liam Aiken is an American actor known for his roles as a child and teen in films such as "A Series of Unfortunate Events," "Good Boy!" and "Stepmom."
  • 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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd799d50388190bf2b7dfdd90949e9 completed March 20, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee0815d848190bacd5ec6a778d91e completed March 21, 2026, 6:16 p.m.
Created at: March 20, 2026, 1:46 p.m.