Triple

T12522607
Position Surface form Disambiguated ID Type / Status
Subject This Way Please E299355 entity
Predicate screenwriter P2831 FINISHED
Object Karl Tunberg E288330 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: Karl Tunberg | Statement: [This Way Please, screenwriter, Karl Tunberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl Tunberg
Context triple: [This Way Please, screenwriter, Karl Tunberg]
  • A. Karl Tunberg chosen
    Karl Tunberg was an American screenwriter best known for writing the screenplay of the epic 1959 film "Ben-Hur."
  • B. William Tunberg
    William Tunberg was an American screenwriter best known for adapting the classic 1957 Disney film "Old Yeller."
  • C. Carl Kjeldsberg
    Carl Kjeldsberg is a pathologist and academic leader best known as a co-founder of ARUP Laboratories, a major national clinical and anatomic pathology reference laboratory.
  • D. Karl Sodersten
    Karl Sodersten is a film editor known for his work on the Australian psychological thriller "Lantana."
  • E. Christian Lundeberg
    Christian Lundeberg was a Swedish conservative politician who briefly served as Prime Minister of Sweden in 1905 during the dissolution of the union with Norway.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9545c2aa081908e8a5a94d30e23eb completed April 10, 2026, 7:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc159c88190835fea5c0d9ee799 completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.