Triple

T18216150
Position Surface form Disambiguated ID Type / Status
Subject Mary Jamison E436163 entity
Predicate hasRelative P367 FINISHED
Object Matt Jamison 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: Matt Jamison | Statement: [Mary Jamison, hasRelative, Matt Jamison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Jamison
Context triple: [Mary Jamison, hasRelative, Matt Jamison]
  • A. Matt Jamison chosen
    Matt Jamison is a fictional Episcopal priest and central character in the television series "The Leftovers," known for his deep faith and personal struggles.
  • B. Ray Marler
    Ray Marler is a local political figure who serves as the mayor of Headland, Alabama.
  • C. Matt Eversmann
    Matt Eversmann is a former U.S. Army Ranger sergeant known for his leadership during the 1993 Battle of Mogadishu, later depicted in the film "Black Hawk Down."
  • D. Marc Slayton
    Marc Slayton is a fictional superhero better known as Backlash, a covert operative and martial artist from the WildStorm comic universe.
  • E. Jason Tynes
    Jason Tynes is known primarily as the brother of former NFL placekicker Lawrence Tynes.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47765a081908d0bbca1245f89ba completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.