Triple

T7049479
Position Surface form Disambiguated ID Type / Status
Subject How to Steal a Million E163727 entity
Predicate editedBy P1954 FINISHED
Object Robert Swink E255026 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: Robert Swink | Statement: [How to Steal a Million, editedBy, Robert Swink]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Swink
Context triple: [How to Steal a Million, editedBy, Robert Swink]
  • A. Robert Swink chosen
    Robert Swink was an American film editor known for his work on numerous classic Hollywood films, including "Roman Holiday."
  • B. Peter Schink
    Peter Schink is a screenwriter best known for co-writing the apocalyptic action-horror film "Legion" (2010).
  • C. Donald Oenslager
    Donald Oenslager was an influential American theatrical set designer and educator known for helping shape modern stage design on Broadway in the mid-20th century.
  • D. Roy Leenig
    Roy Leenig was a prominent American college basketball coach best known for his successful tenure leading the Holy Cross Crusaders men's basketball program.
  • E. James D. van Hoften
    James D. van Hoften is a former NASA astronaut and aerospace engineer who flew on multiple Space Shuttle missions, notably performing spacewalks to repair satellites.
  • 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_69c6885f598c8190b6b6495c59d8d962 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e24d5e8c8190b37e56107e6da8ab completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7888bba9c8190b6414b56e5588ec0 completed March 28, 2026, 7:51 a.m.
Created at: March 27, 2026, 2:37 p.m.