Triple

T17606932
Position Surface form Disambiguated ID Type / Status
Subject Michael Biehn E428856 entity
Predicate familyName P18 FINISHED
Object Biehn 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: Biehn | Statement: [Michael Biehn, familyName, Biehn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Biehn
Context triple: [Michael Biehn, familyName, Biehn]
  • A. Biehn chosen
    Biehn is the surname of American actor Michael Biehn, known for his roles in science fiction and action films such as The Terminator and Aliens.
  • B. Veit Renn
    Veit Renn is a music producer best known for his work on major pop projects, including *No Strings Attached* by NSYNC.
  • C. Darel
    Darel is a given name, typically a variant spelling of Daryl, used for both males and females.
  • D. Guion
    Guion is a surname of French origin historically associated with several notable families and individuals.
  • E. Andor Knorr
    Andor Knorr is a Hungarian figure known primarily through his familial connection to Adam Sors, a character from the novel and film "Sunshine" that traces the fortunes of a Jewish Hungarian family across generations.
  • 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_69d889e1c6148190ba76241e74688f8b completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46c4ccef08190aeaa88670364bd74 completed April 19, 2026, 5:46 a.m.
Created at: April 10, 2026, 5:51 a.m.