Triple

T19526375
Position Surface form Disambiguated ID Type / Status
Subject Ben Maddow E488527 entity
Predicate familyName P18 FINISHED
Object Maddow 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: Maddow | Statement: [Ben Maddow, familyName, Maddow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maddow
Context triple: [Ben Maddow, familyName, Maddow]
  • A. Rachel Maddow chosen
    Rachel Maddow is an American television news host, political commentator, and author best known for anchoring "The Rachel Maddow Show" on MSNBC.
  • B. The Rachel Maddow Show
    The Rachel Maddow Show is a primetime American news and opinion television program hosted by political commentator Rachel Maddow, known for its in-depth analysis of U.S. politics and current events.
  • C. Ben Maddow
    Ben Maddow was an American screenwriter and documentary filmmaker known for his work on classic mid-20th-century films and socially conscious cinema.
  • D. Samantha Bee
    Samantha Bee is a Canadian-American comedian, writer, and political satirist best known for her work as a correspondent on The Daily Show and as the host of the late-night show Full Frontal with Samantha Bee.
  • E. Merrie Hannity
    Merrie Hannity is the daughter of American conservative television and radio host Sean Hannity.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363aeb8c8190be2bdd73e421af96 completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.