Triple

T21512024
Position Surface form Disambiguated ID Type / Status
Subject Samantha Bee E530749 entity
Predicate familyName P18 FINISHED
Object Bee 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: Bee | Statement: [Samantha Bee, familyName, Bee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bee
Context triple: [Samantha Bee, familyName, Bee]
  • A. Bee chosen
    Bee is a common English surname shared by various individuals, including the comedian and television host Samantha Bee.
  • B. the Bee
    The Bee is a former name meaning associated with the genus Musca, historically used to denote a bee-like characteristic or identity.
  • C. Hornisse
    Hornisse is the German nickname given to the Messerschmitt Me 410, a World War II twin-engine heavy fighter and fast bomber used by the Luftwaffe.
  • D. Wasp
    "Wasp" is an acclaimed 2003 British short film written and directed by Andrea Arnold, known for its gritty portrayal of a struggling single mother and for winning the Academy Award for Best Live Action Short Film.
  • E. Wasp
    "Wasp" is a 1957 science fiction novel by Eric Frank Russell, best known for its satirical portrayal of psychological warfare and guerrilla tactics used by a single operative to destabilize an alien empire.
  • 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_69e0c45c81f08190a6b8bbb70a45aae7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea8779c081908171c58d345d54ae completed April 23, 2026, 9:46 a.m.
Created at: April 16, 2026, 6:25 p.m.