Triple

T11667335
Position Surface form Disambiguated ID Type / Status
Subject Carol Hughes E277282 entity
Predicate spouse P13 FINISHED
Object Frank Faylen E597435 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 Faylen | Statement: [Carol Hughes, spouse, Frank Faylen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Faylen
Context triple: [Carol Hughes, spouse, Frank Faylen]
  • A. Frank Faylen chosen
    Frank Faylen was an American character actor best known for his supporting roles in classic films like "It's a Wonderful Life" and "The Lost Weekend," as well as numerous television appearances.
  • B. Ben Fankhauser
    Ben Fankhauser is an American stage actor and singer best known for originating the role of Davey in the Broadway production of the musical "Newsies."
  • C. Russell Faibisch
    Russell Faibisch is an American music promoter and entrepreneur best known for creating and developing the globally renowned Ultra Music Festival electronic dance music brand.
  • D. Jeremy Furstenfeld
    Jeremy Furstenfeld is the drummer of the American alternative rock band Blue October.
  • E. Anthony Ashnault
    Anthony Ashnault is an American wrestler best known as a multiple-time All-American and NCAA champion for Rutgers University.
  • 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_69d6aafd0a448190b44da30af8c6c519 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a43f438081909da476294a057c38 completed April 10, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69f08fbb28548190af494ddf1a1ff986 completed April 28, 2026, 10:45 a.m.
Created at: April 8, 2026, 9:39 p.m.