Triple

T20994721
Position Surface form Disambiguated ID Type / Status
Subject Peggy Mitchell E517117 entity
Predicate spouse P13 FINISHED
Object Frank Butcher 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: Frank Butcher | Statement: [Peggy Mitchell, spouse, Frank Butcher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Butcher
Context triple: [Peggy Mitchell, spouse, Frank Butcher]
  • A. Frank Butcher chosen
    Frank Butcher is a fictional wheeler-dealer and market trader from the BBC soap opera "EastEnders," known for his loud suits, chaotic love life, and comic yet tragic storylines.
  • B. Frank Bunce
    Frank Bunce is a former New Zealand rugby union centre best known for his influential international career with the All Blacks in the 1990s.
  • C. Frank Butler
    Frank Butler was an American screenwriter and actor best known for his work on classic Hollywood films, including co-writing the Oscar-winning screenplay for "Going My Way."
  • D. Frank Butler
    Frank Butler is the charming sharpshooter and romantic lead opposite Annie Oakley in the musical film "Annie Get Your Gun."
  • E. Rich Buckler
    Rich Buckler was an American comic book artist best known for his work at Marvel and DC Comics, including notable runs on titles like Fantastic Four and Deathlok.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc1e75188190a97114238ea0b4f9 completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:50 p.m.