Triple

T17977255
Position Surface form Disambiguated ID Type / Status
Subject Jenna Elfman E449505 entity
Predicate participatedIn P149 FINISHED
Object Edtv 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: Edtv | Statement: [Jenna Elfman, participatedIn, Edtv]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edtv
Context triple: [Jenna Elfman, participatedIn, Edtv]
  • A. Edtv chosen
    Edtv is a 1999 American comedy film directed by Ron Howard about an ordinary man whose life is turned into a nonstop reality TV show.
  • B. CDTV
    CDTV is a multimedia home entertainment and computing system developed by Commodore based on Amiga technology, combining a CD-ROM player with a personal computer.
  • C. EE TV
    EE TV is a UK-based digital television and streaming service offered by the mobile network operator EE, providing access to live channels, on-demand content, and premium sports and entertainment.
  • D. ETNT
    ETNT is the ICAO airport code assigned to Wittmundhafen Air Base, a German military airfield.
  • E. ESTV
    ESTV is the German abbreviation for Switzerland’s Federal Tax Administration, the national authority responsible for implementing and overseeing federal tax laws.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b20010c8819088c022565183a7ff completed April 19, 2026, 10:44 a.m.
Created at: April 10, 2026, 10:22 a.m.