Triple

T3156706
Position Surface form Disambiguated ID Type / Status
Subject Today E66000 entity
Predicate notableHost P5272 FINISHED
Object Katie Couric E162293 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: Katie Couric | Statement: [Today, notableHost, Katie Couric]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katie Couric
Context triple: [Today, notableHost, Katie Couric]
  • A. Katie Couric chosen
    Katie Couric is an American journalist and television personality best known for anchoring major network news programs such as NBC's Today and the CBS Evening News.
  • B. Savannah Guthrie
    Savannah Guthrie is an American broadcast journalist and attorney best known as a longtime co-anchor of NBC’s morning show "Today."
  • C. Judy Woodruff
    Judy Woodruff is an American broadcast journalist best known for her long tenure as a leading anchor and managing editor of PBS’s flagship news program.
  • D. Diane Sawyer
    Diane Sawyer is an American television journalist best known for anchoring ABC News programs such as "ABC World News" and "Good Morning America."
  • E. Meredith Vieira
    Meredith Vieira is an American broadcast journalist and television personality best known for co-hosting NBC's "Today" and moderating the daytime talk show "The View."
  • 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_69ad85850c1481908a9e9c6242238de2 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada5eafa4c8190a65cc1312823144c completed March 8, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3b513248190a94c2f7642151515 completed March 12, 2026, 5:11 p.m.
Created at: March 8, 2026, 3:05 p.m.