Triple

T4369018
Position Surface form Disambiguated ID Type / Status
Subject The Toll of the Sea E98848 entity
Predicate starring P1507 FINISHED
Object Kenneth Harlan E407987 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: Kenneth Harlan | Statement: [The Toll of the Sea, starring, Kenneth Harlan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kenneth Harlan
Context triple: [The Toll of the Sea, starring, Kenneth Harlan]
  • A. Kenneth Harlan chosen
    Kenneth Harlan was an American film actor best known for his prolific work in silent films and early talkies during the 1910s–1930s.
  • B. Walter Dellinger
    Walter Dellinger was a prominent American constitutional law scholar and former acting U.S. Solicitor General known for his influential work in Supreme Court advocacy and legal academia.
  • C. Russell Harlan
    Russell Harlan was an American cinematographer known for his work on numerous classic films, including "Witness for the Prosecution," "To Kill a Mockingbird," and "Red River."
  • D. Andrew Harlan
    Andrew Harlan is the time-manipulating Technician protagonist of Isaac Asimov’s science fiction novel "The End of Eternity."
  • E. Carl Graves
    Carl Graves is a musician best known for his role as a member of the American new wave band Oingo Boingo.
  • 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_69b3454db3708190aeafd814413c4c3d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352052b388190b02cca9a3b480be4 completed March 12, 2026, 11:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5dbd1646c8190b7db5d9a9445633c completed March 14, 2026, 10:06 p.m.
Created at: March 12, 2026, 11:17 p.m.