Triple

T16709048
Position Surface form Disambiguated ID Type / Status
Subject Tom Brokaw E406052 entity
Predicate earlyCareerAt P124314 FINISHED
Object KMTV E406052 NE FINISHED

How this triple was built (3 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: KMTV | Statement: [Tom Brokaw, earlyCareerAt, KMTV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KMTV
Context triple: [Tom Brokaw, earlyCareerAt, KMTV]
  • A. KMTV chosen
    KMTV is a local television station where journalist Tom Brokaw began his early broadcasting career.
  • B. KMTJ
    KMTJ is the ICAO airport code for Montrose Regional Airport in Montrose, Colorado, a commercial airport serving the western Colorado region and nearby mountain resort areas.
  • C. KBTV
    KBTV is the ICAO airport code for Burlington International Airport, a primary commercial airport serving Burlington, Vermont, and the surrounding region.
  • D. KMSP-TV
    KMSP-TV is a Fox-affiliated television station serving the Minneapolis–Saint Paul metropolitan area.
  • E. İctimai Television
    İctimai Television is Azerbaijan’s national public broadcaster, known internationally for organizing and airing major events such as the Eurovision Song Contest.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: earlyCareerAt
Context triple: [Tom Brokaw, earlyCareerAt, KMTV]
  • A. earlyCareerActivity
    Indicates activities, roles, or engagements undertaken by an entity during the early stage of its career or professional development.
  • B. earlyCareerCoach
    Indicates that one entity serves as a coach or mentor to another during the early stage of that other entity’s career.
  • C. youthCareerStart
    Indicates the point in time when an individual began their youth-level career or involvement in an activity, typically before turning professional.
  • D. studCareerBegan
    Indicates that a student's professional or academic career started at a specified time or institution.
  • E. careerStart
    Indicates the point in time when an entity begins its professional career or main occupational activity.
  • F. None of above. chosen

Provenance (5 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_69d8838db21081909589220fd71440a4 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e38650c3808190a561f22b169dc3ae completed April 18, 2026, 1:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0091a739308190b4d645e096d1710b completed May 10, 2026, 2:09 p.m.
PD Predicate disambiguation batch_69e319c379f88190ac0adf812486f598 completed April 18, 2026, 5:42 a.m.
PDg Predicate description generation batch_69e326b9e84881909a9166e65bd850d6 completed April 18, 2026, 6:37 a.m.
Created at: April 10, 2026, 5:20 a.m.