Triple

T10920104
Position Surface form Disambiguated ID Type / Status
Subject Thaddeus Ross E257924 entity
Predicate relative P37 FINISHED
Object Betty Ross E760521 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: Betty Ross | Statement: [Thaddeus Ross, relative, Betty Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betty Ross
Context triple: [Thaddeus Ross, relative, Betty Ross]
  • A. Betty Ross chosen
    Betty Ross is a Marvel Comics character best known as a brilliant scientist and the longtime romantic partner of Bruce Banner, the Hulk.
  • B. Betty Ross Clarke
    Betty Ross Clarke was an American stage and film actress active in the early 20th century, known for her roles in both silent and sound-era productions.
  • C. Jean Craddock
    Jean Craddock is a young journalist and single mother who becomes romantically involved with aging country singer Bad Blake in the film "Crazy Heart."
  • D. Yeoman Janice Rand
    Yeoman Janice Rand is a recurring Star Trek character who serves as Captain Kirk’s personal yeoman aboard the USS Enterprise in the original television series.
  • E. Vicki Harper
    Vicki Harper is known as the former spouse of Australian film director Phillip Noyce.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d77081a0c48190b7aa4a482032d1ea completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2171adbbc8190916a5463b6e5c186 completed April 17, 2026, 11:18 a.m.
Created at: April 8, 2026, 9:22 p.m.