Triple

T14723118
Position Surface form Disambiguated ID Type / Status
Subject Berlin Station E345863 entity
Predicate starring P1507 FINISHED
Object Michelle Forbes E908892 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: Michelle Forbes | Statement: [Berlin Station, starring, Michelle Forbes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelle Forbes
Context triple: [Berlin Station, starring, Michelle Forbes]
  • A. Michelle Forbes chosen
    Michelle Forbes is an American actress known for her intense, often complex roles in television series such as "Star Trek: The Next Generation," "Homicide: Life on the Street," and "True Blood."
  • B. Anne Alexander
    Anne Alexander is a person known primarily as a relative of John Alexander, though specific public details about her life or work are not widely documented.
  • C. Oonagh Paige Heard
    Oonagh Paige Heard is the daughter of American actress Amber Heard, born via surrogate in 2021.
  • D. Jennifer Mercer
    Jennifer Mercer is a member of the wealthy and politically influential Mercer family, known primarily as the sister of conservative donor Rebekah Mercer.
  • E. Fortune Feimster
    Fortune Feimster is an American stand-up comedian, writer, and actress known for her self-deprecating humor and roles in television and film comedies.
  • 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_69d822e5911c8190ba589f957dbd9ba7 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec25e9a14819081fa06fc601f295d completed April 14, 2026, 10:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf0957bb081908f1f382f3be8ec20 completed May 8, 2026, 2:17 p.m.
Created at: April 10, 2026, 1:29 a.m.