Triple

T17861976
Position Surface form Disambiguated ID Type / Status
Subject Ivan Tors E446094 entity
Predicate workedOn P3 FINISHED
Object Sea Hunt (TV series) E981149 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: Sea Hunt (TV series) | Statement: [Ivan Tors, workedOn, Sea Hunt (TV series)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sea Hunt (TV series)
Context triple: [Ivan Tors, workedOn, Sea Hunt (TV series)]
  • A. Sea Hunt chosen
    Sea Hunt is a late-1950s American adventure television series centered on the underwater exploits of scuba diver Mike Nelson, played by Lloyd Bridges.
  • B. Gilligan
    Gilligan is the bumbling, well-meaning first mate and central comedic figure from the classic American television sitcom "Gilligan's Island."
  • C. Cape Shore
    Cape Shore is a coastal region on Newfoundland’s Avalon Peninsula known for its scenic shoreline, small fishing communities, and cultural heritage.
  • D. Magnum, P.I.
    Magnum, P.I. is an American television crime drama series from the 1980s that follows the adventures of private investigator Thomas Magnum in Hawaii.
  • E. Gilligan's Island
    Gilligan's Island is a classic 1960s American sitcom about a group of castaways stranded on a deserted island, known for its ensemble characters and enduring pop-culture impact.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e49790ea148190b7a966812d44f430 completed April 19, 2026, 8:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a031b1afca88190ba375668392ef844 completed May 12, 2026, 12:20 p.m.
Created at: April 10, 2026, 10:17 a.m.