Triple

T10845299
Position Surface form Disambiguated ID Type / Status
Subject The Well E255994 entity
Predicate starring P1507 FINISHED
Object Frank Wilson E232587 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: Frank Wilson | Statement: [The Well, starring, Frank Wilson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Wilson
Context triple: [The Well, starring, Frank Wilson]
  • A. Frank Wilson chosen
    Frank Wilson was an American songwriter and record producer best known for his influential work with Motown Records in the 1960s and 1970s.
  • B. Don W. Wilson
    Don W. Wilson is an American archivist and historian who served as the head of the U.S. National Archives and Records Administration.
  • C. Dick Wilson
    Dick Wilson was a prominent American golf course architect known for designing numerous challenging and strategically sophisticated courses in the mid-20th century.
  • D. Donald Wilson
    Donald Wilson was a British television producer and writer best known for helping develop and launch the long-running science fiction series Doctor Who for the BBC in the early 1960s.
  • E. Donald Wilson
    Donald Wilson was a prominent U.S. Army Air Corps officer and airpower theorist who helped shape early American air doctrine in the interwar period.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d750d0155c81908fb55ba6b45db800 completed April 9, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69e4417f4dfc8190bd50cec0bc52a9cc completed April 19, 2026, 2:44 a.m.
Created at: April 8, 2026, 9:19 p.m.