Triple

T20375837
Position Surface form Disambiguated ID Type / Status
Subject Arli$$ E497689 entity
Predicate starring P1507 FINISHED
Object Michael Boatman 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: Michael Boatman | Statement: [Arli$$, starring, Michael Boatman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Boatman
Context triple: [Arli$$, starring, Michael Boatman]
  • A. Michael Boatman chosen
    Michael Boatman is an American actor and writer best known for his comedic and dramatic television roles in series such as Spin City and The Good Wife.
  • B. Declan Whitebloom
    Declan Whitebloom is a British music video director known for his visually polished work with major pop artists.
  • C. Colin Morgan
    Colin Morgan is a Northern Irish actor best known for his title role in the BBC fantasy series "Merlin" and various acclaimed stage and screen performances.
  • D. Angus Cloud
    Angus Cloud was an American actor best known for his breakout role as the lovable drug dealer Fezco on HBO's teen drama series "Euphoria."
  • E. Caleb Landry Jones
    Caleb Landry Jones is an American actor and musician known for his intense, often unsettling performances in films such as "Get Out," "Three Billboards Outside Ebbing, Missouri," and "Nitram."
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678acae3c8190ae04323760bf5597 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.