Triple

T14964950
Position Surface form Disambiguated ID Type / Status
Subject Marge Gunderson E373166 entity
Predicate givenName P17 FINISHED
Object Marge E373166 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: Marge | Statement: [Marge Gunderson, givenName, Marge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marge
Context triple: [Marge Gunderson, givenName, Marge]
  • A. Marge Simpson
    Marge Simpson is the blue-haired, patient, and moral center of the Simpson family on the long-running animated television series "The Simpsons."
  • B. Marge Gunderson chosen
    Marge Gunderson is the pregnant, small-town Minnesota police chief known for her calm competence and moral clarity in the film "Fargo."
  • C. Lisa Simpson
    Lisa Simpson is the intelligent, saxophone-playing, socially conscious middle child of the Simpson family on the animated television series "The Simpsons."
  • D. Maggie Simpson
    Maggie Simpson is the pacifier-sucking infant daughter of the Simpson family in the animated television series "The Simpsons."
  • E. Maude Flanders
    Maude Flanders is a devout, conservative Christian homemaker and the late wife of Ned Flanders on the animated television series "The Simpsons."
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e2fdcc8190bffe603db3388736 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe969112d8819094e5d81a8ffa3b8a completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:46 a.m.