Triple

T17865239
Position Surface form Disambiguated ID Type / Status
Subject Invaders from Mars E446680 entity
Predicate hasCastMember P2308 FINISHED
Object Jimmy Hunt 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: Jimmy Hunt | Statement: [Invaders from Mars, hasCastMember, Jimmy Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jimmy Hunt
Context triple: [Invaders from Mars, hasCastMember, Jimmy Hunt]
  • A. Jimmy Hunt chosen
    Jimmy Hunt is an American former child actor best known for his leading role in the 1953 science fiction film "Invaders from Mars."
  • B. Jock Lindsey
    Jock Lindsey is a fictional pilot and side character from the Indiana Jones franchise, known as Indy’s adventurous aviator friend.
  • C. Al Hunt
    Al Hunt is an American journalist and political commentator known for his long tenure at The Wall Street Journal and his work on television public affairs programs.
  • D. Jock Cunningham
    Jock Cunningham was a prominent Scottish volunteer and military commander in the Spanish Civil War, noted for his leadership in the International Brigades.
  • E. Jack McManus
    Jack McManus is a British singer-songwriter and musician known for his work in pop and adult contemporary music and for his marriage to actress and singer Martine McCutcheon.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49793a2588190bb341ac606d767fe completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.