Triple

T3998240
Position Surface form Disambiguated ID Type / Status
Subject Tom Brokaw E87148 entity
Predicate hasChild P369 FINISHED
Object Sarah Brokaw E410124 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: Sarah Brokaw | Statement: [Tom Brokaw, hasChild, Sarah Brokaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Brokaw
Context triple: [Tom Brokaw, hasChild, Sarah Brokaw]
  • A. Jennifer Brokaw chosen
    Jennifer Brokaw is an American physician and patient advocate, best known as the daughter of longtime NBC news anchor Tom Brokaw.
  • B. Carole Shorenstein Hays
    Carole Shorenstein Hays is an American theatrical producer and former co-owner of San Francisco’s Curran Theatre, known for bringing major Broadway productions to the West Coast.
  • C. Robin Lawford
    Robin Lawford is a member of the prominent Lawford family, related to actor Peter Lawford and connected to the extended Kennedy family.
  • D. Jane Pauley
    Jane Pauley is an American television journalist and news anchor best known for her long tenure as co-host of NBC's "Today" and later work on programs like "Dateline NBC" and "CBS Sunday Morning."
  • E. Tom Brokaw
    Tom Brokaw is an American television journalist and author best known for serving as a longtime anchor and managing editor of NBC Nightly News.
  • 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_69aed94118148190975e6aa4e554cde9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefa3ef7ac8190abe02f440ff83c43 completed March 9, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56b4447e08190aa90dd50f304a491 completed March 14, 2026, 2:05 p.m.
Created at: March 9, 2026, 3:34 p.m.