Triple

T13240132
Position Surface form Disambiguated ID Type / Status
Subject Michelle Dockery E315258 entity
Predicate familyName P18 FINISHED
Object Dockery E315258 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: Dockery | Statement: [Michelle Dockery, familyName, Dockery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dockery
Context triple: [Michelle Dockery, familyName, Dockery]
  • A. Dockery chosen
    Dockery is an English surname most notably associated with actress Michelle Dockery, known for her role in the television series "Downton Abbey."
  • B. Delly
    Delly is the nickname of Australian professional basketball player Matthew Dellavedova, known for his gritty defense and tenure in the NBA, including a championship run with the Cleveland Cavaliers.
  • C. Dortch
    Dortch is a surname most notably associated with Helen Dortch Longstreet, an American social reformer, suffragist, and the second wife of Confederate General James Longstreet.
  • D. Guardbridge
    Guardbridge is a small Scottish village in Fife, situated near the River Eden and known historically for its paper mill and as a gateway to St Andrews.
  • E. Haralson
    Haralson is an unincorporated rural community located in Coweta County, Georgia, United States.
  • 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_69d806b1072881909e46bd212259c5f0 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98d5850ac8190849a51da39efe5be completed April 10, 2026, 11:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff323a3c8190b46b24e69e653105 completed May 3, 2026, 7:54 a.m.
Created at: April 9, 2026, 9:23 p.m.