Triple

T8395813
Position Surface form Disambiguated ID Type / Status
Subject James Gunn E198048 entity
Predicate spouse P13 FINISHED
Object Jenna Fischer E223036 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: Jenna Fischer | Statement: [James Gunn, spouse, Jenna Fischer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jenna Fischer
Context triple: [James Gunn, spouse, Jenna Fischer]
  • A. Jenna Fischer chosen
    Jenna Fischer is an American actress best known for her role as Pam Beesly on the hit sitcom "The Office."
  • B. Kristin Davis
    Kristin Davis is an American actress best known for her role as Charlotte York on the television series "Sex and the City" and its related films.
  • C. Megan Mullally
    Megan Mullally is an American actress, comedian, and singer best known for her Emmy-winning role as Karen Walker on the television sitcom "Will & Grace."
  • D. Cobie Smulders
    Cobie Smulders is a Canadian actress best known for her role as Robin Scherbatsky on the sitcom "How I Met Your Mother" and for portraying Maria Hill in the Marvel Cinematic Universe.
  • E. Rashida Jones
    Rashida Jones is an American actress, writer, and producer known for roles in television series like "Parks and Recreation" and films such as "The Social Network," as well as her work behind the scenes as a screenwriter and filmmaker.
  • 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb81874d6c8190bbc0ac832d8a339d completed March 31, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde85ee7b08190bfbcbed0edb142dd completed April 2, 2026, 3:54 a.m.
Created at: March 30, 2026, 6:04 p.m.