Triple

T11151347
Position Surface form Disambiguated ID Type / Status
Subject Arliss Howard E263792 entity
Predicate notableWork P4 FINISHED
Object Medium (TV series) E222518 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: Medium (TV series) | Statement: [Arliss Howard, notableWork, Medium (TV series)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Medium (TV series)
Context triple: [Arliss Howard, notableWork, Medium (TV series)]
  • A. Medium (TV series) chosen
    Medium is an American supernatural drama television series that follows a woman who uses her psychic abilities to help solve crimes.
  • B. The Medium
    The Medium is a short, two-act English-language opera by Gian Carlo Menotti that blends psychological drama and the supernatural, first premiered in 1946.
  • C. Easy (TV series)
    Easy is an American anthology comedy-drama television series created by Joe Swanberg that explores modern love, relationships, and technology through loosely connected stories set in Chicago.
  • D. Mitjans
    Mitjans is the family name of Francesc Mitjans i Miró, a notable Spanish architect associated with modernist architecture in Barcelona.
  • E. Are Media
    Are Media is a major Australian magazine and digital media company that publishes a wide range of lifestyle, fashion, and entertainment titles.
  • 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_69d6aa9ccddc8190868998c8b7beb060 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8719e74819095413abc6c79296c completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4422ca62c81909a3a935fb7e28c34 completed April 19, 2026, 2:47 a.m.
Created at: April 8, 2026, 9:28 p.m.