Triple

T21282043
Position Surface form Disambiguated ID Type / Status
Subject Frances Gumm E524549 entity
Predicate spouse P13 FINISHED
Object Mark Herron 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: Mark Herron | Statement: [Frances Gumm, spouse, Mark Herron]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Herron
Context triple: [Frances Gumm, spouse, Mark Herron]
  • A. Mark Herron chosen
    Mark Herron was an American actor best known for being the fourth husband of legendary entertainer Judy Garland.
  • B. Alex Herron
    Alex Herron is a Norwegian music video and film director known for his work on numerous pop and rock videos as well as genre films.
  • C. Derek Hatton
    Derek Hatton is a British former Labour politician best known as the outspoken deputy leader of Liverpool City Council in the 1980s and a prominent figure in the Trotskyist Militant tendency.
  • D. Mark Holbrook
    Mark Holbrook is a notable individual whose prominence has led to his recognition as a distinguished bearer of the Holbrook surname.
  • E. Darryl Hickman
    Darryl Hickman is an American former child actor and film and television performer known for roles in classic Hollywood films and later work as a television executive and acting coach.
  • 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736d249fc8190b0b310467ddeac3c completed April 21, 2026, 8:35 a.m.
Created at: April 16, 2026, 4:02 p.m.