Triple

T11344223
Position Surface form Disambiguated ID Type / Status
Subject Sally Draper E268676 entity
Predicate stepmother P14091 FINISHED
Object Megan Draper E920602 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: Megan Draper | Statement: [Sally Draper, stepmother, Megan Draper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Megan Draper
Context triple: [Sally Draper, stepmother, Megan Draper]
  • A. Megan Draper chosen
    Megan Draper is a character on the television series "Mad Men," known as Don Draper’s second wife and an aspiring actress who transitions from copywriter to performer.
  • B. Mellie Logan
    Mellie Logan is a sharp-witted, resourceful sister in the film "Logan Lucky," known for her crucial role in helping execute the heist.
  • C. Sally Draper
    Sally Draper is the sharp, increasingly independent daughter of Don and Betty Draper in the television series "Mad Men," whose coming-of-age story reflects the social upheavals of 1960s America.
  • D. Kate Silverton
    Kate Silverton is a British journalist and television presenter best known for her work as a BBC newsreader and documentary host.
  • E. Marcia Griffin
    Marcia Griffin, better known as Marcia Lucas, is an American film editor renowned for her Oscar-winning work on the original Star Wars trilogy and her influential contributions to 1970s New Hollywood cinema.
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea1f9574819089760c5b5908f09e completed April 9, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e55649a9188190911608fef5894bd8 completed April 19, 2026, 10:25 p.m.
Created at: April 8, 2026, 9:33 p.m.