Triple

T19627770
Position Surface form Disambiguated ID Type / Status
Subject Broken Arrow E471182 entity
Predicate stars P1956 FINISHED
Object Samantha Mathis 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: Samantha Mathis | Statement: [Broken Arrow, stars, Samantha Mathis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samantha Mathis
Context triple: [Broken Arrow, stars, Samantha Mathis]
  • A. Samantha Mathis chosen
    Samantha Mathis is an American actress known for her work in films and television since the late 1980s, including prominent roles in movies like "Pump Up the Volume," "Little Women," and "American Psycho."
  • B. Courtney Eaton
    Courtney Eaton is an Australian actress and model best known for her roles in action and fantasy films such as "Mad Max: Fury Road" and "Gods of Egypt."
  • C. Courtney Matthews
    Courtney Matthews is a fictional character from the soap opera "General Hospital," known for her complex relationships and dramatic storylines in Port Charles.
  • D. Samantha Gates
    Samantha Gates is a British former child actress best known for her role in the 1978 animated/live-action film "The Water Babies."
  • E. Samantha Stephens
    Samantha Stephens is the magically gifted suburban housewife and central witch protagonist of the classic American television sitcom "Bewitched."
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640eadcc48190ab5e36ddcde0c328 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.