Triple

T20383827
Position Surface form Disambiguated ID Type / Status
Subject Ship Ahoy E497907 entity
Predicate hasCastMember P2308 FINISHED
Object William Post Jr. 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: William Post Jr. | Statement: [Ship Ahoy, hasCastMember, William Post Jr.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Post Jr.
Context triple: [Ship Ahoy, hasCastMember, William Post Jr.]
  • A. William Post Jr. chosen
    William Post Jr. was an American character actor active in the mid-20th century, known for his supporting roles in films and early television, including appearances in mystery and crime dramas.
  • B. Tim Tibbetts
    Tim Tibbetts is an individual notable enough to be specifically cited as a bearer of the surname Tibbetts.
  • C. George Tibbets
    George Tibbets is a person notable enough to be recognized as a bearer of the surname Tibbets, though specific widely known biographical details about him are not well documented.
  • D. John C. Tibbets
    John C. Tibbets is an American film historian, author, and former television broadcaster known for his work on cinema history and interviews with prominent filmmakers and actors.
  • E. Harold Howland
    Harold Howland was an American writer and editor known for his essays and contributions to early 20th-century magazines.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.