Triple

T15600689
Position Surface form Disambiguated ID Type / Status
Subject Magazine Management Company E375022 entity
Predicate owner P347 FINISHED
Object Martin Goodman E1167366 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: Martin Goodman | Statement: [Magazine Management Company, owner, Martin Goodman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martin Goodman
Context triple: [Magazine Management Company, owner, Martin Goodman]
  • A. Martin Goodman
    Martin Goodman was a prominent Toronto civic leader and former president of the Toronto Star, remembered for his contributions to the city’s public life and urban development.
  • B. Martin Goodman
    Martin Goodman is the eccentric, food-obsessed and often childish father in the British sitcom "Friday Night Dinner," known for his bizarre habits and catchphrases.
  • C. Martin Goodman chosen
    Martin Goodman was an American publisher best known for building the pulp magazine and comic book empire that eventually evolved into Marvel Comics.
  • D. Robert Levine
    Robert Levine is an American cardiologist best known as the husband of actress Mary Tyler Moore.
  • E. Stephen Frank
    Stephen Frank was an early American pioneer after whom the city of Frankfort, Kentucky, is named.
  • 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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e621fc4819097e8e85e7ddfdc6c completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f355ff48190a2c2c262c09e6de0 completed May 9, 2026, 4:22 p.m.
Created at: April 10, 2026, 4:12 a.m.