Triple

T17018330
Position Surface form Disambiguated ID Type / Status
Subject Search Party E412878 entity
Predicate leadCharacter P1668 FINISHED
Object Dory Sief E1245546 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: Dory Sief | Statement: [Search Party, leadCharacter, Dory Sief]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dory Sief
Context triple: [Search Party, leadCharacter, Dory Sief]
  • A. Dory Sief chosen
    Dory Sief is the increasingly unhinged, morally conflicted protagonist of the dark comedy series "Search Party," whose obsession with finding a missing acquaintance spirals into crime and chaos.
  • B. Daria Morgendorffer
    Daria Morgendorffer is the intelligent, sarcastic, and socially detached teenage protagonist of the animated TV series "Daria," known for her deadpan wit and critical view of high school life and suburban culture.
  • C. Dorys Madden
    Dorys Madden is best known as the wife of Basketball Hall of Famer Julius "Dr. J" Erving.
  • D. Dori Bridges
    Dori Bridges is known as the former wife of American actor Todd Bridges, who starred as Willis Jackson on the classic sitcom "Diff'rent Strokes."
  • E. Sally Lapiduss
    Sally Lapiduss is an American television producer and writer known for her work on numerous sitcoms and comedy series.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d480a58c8190a3912d26debb4311 completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01233311648190b5f8a8e7c209d124 completed May 11, 2026, 12:30 a.m.
Created at: April 10, 2026, 5:33 a.m.