Triple

T3433357
Position Surface form Disambiguated ID Type / Status
Subject Kristen Stewart E72389 entity
Predicate notableWork P4 FINISHED
Object Seberg E221884 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: Seberg | Statement: [Kristen Stewart, notableWork, Seberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seberg
Context triple: [Kristen Stewart, notableWork, Seberg]
  • A. Jean Seberg chosen
    Jean Seberg was an American actress and French New Wave icon best known for her role in Jean-Luc Godard’s film "Breathless."
  • B. Blue Mitchell
    Blue Mitchell was an American jazz trumpeter known for his lyrical hard bop style and work with leading ensembles in the 1950s and 1960s.
  • C. Dorothy Pennebaker Brando
    Dorothy Pennebaker Brando was an American actress and theater administrator best known as the mother of legendary film actor Marlon Brando.
  • D. Brandon deWilde
    Brandon deWilde was an American child actor best known for his poignant performance as Joey in the classic Western film "Shane."
  • E. Vija Kinski
    Vija Kinski is a key character in Don DeLillo’s novel (and David Cronenberg’s film adaptation) "Cosmopolis," serving as the intellectually incisive chief of theory who engages the protagonist in dense philosophical and economic debates.
  • 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_69ad85ae14308190bcbc25cfa0246c0b completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb9c1d9148190b873ba66d34d4f01 completed March 8, 2026, 6:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3547d3f4c8190bc6811398bd8f080 completed March 13, 2026, 12:04 a.m.
Created at: March 8, 2026, 3:15 p.m.