Triple

T15631094
Position Surface form Disambiguated ID Type / Status
Subject Fairly Legal E375812 entity
Predicate character P662 FINISHED
Object Kate Reed E375817 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: Kate Reed | Statement: [Fairly Legal, character, Kate Reed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Reed
Context triple: [Fairly Legal, character, Kate Reed]
  • A. Kate Reed chosen
    Kate Reed is the sharp, idealistic former lawyer turned mediator at the center of the legal dramedy series "Fairly Legal."
  • B. Alice Brady
    Alice Brady was an American stage and film actress of the early 20th century, best known for her character roles in both silent and sound films and for winning an Academy Award for Best Supporting Actress.
  • C. Marguerite Roberts
    Marguerite Roberts was a prominent American screenwriter known for her sharp dialogue and work on numerous Hollywood films from the 1930s through the 1960s, including the classic Western "True Grit."
  • D. Maud Ellen Dixon
    Maud Ellen Dixon was the wife of New Zealand physicist and science administrator Ernest Marsden.
  • E. Florence Crawford
    Florence Crawford was an early 20th-century Pentecostal evangelist and leader who helped spread the Azusa Street Revival’s message across the United States, particularly through her work in the Pacific Northwest.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eb536348190b93ed3c178d1ffb8 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff678ebe288190bd43a72e99e7aa22 completed May 9, 2026, 4:57 p.m.
Created at: April 10, 2026, 4:14 a.m.