Triple

T22804784
Position Surface form Disambiguated ID Type / Status
Subject Michael D. Steele E564501 entity
Predicate familyName P18 FINISHED
Object Steele NE NERFINISHED

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: Steele | Statement: [Michael D. Steele, familyName, Steele]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steele
Context triple: [Michael D. Steele, familyName, Steele]
  • A. Steele
    Steele is a historic district of the German city of Essen, known for its riverside location along the Ruhr and its blend of residential, commercial, and cultural areas.
  • B. Steele
    Steele is a small city in southeastern Missouri known for its agricultural surroundings and location in Pemiscot County near the Mississippi River.
  • C. Steele chosen
    Steele is a surname most notably borne by Charles Steele Jr., an American civil rights leader and former president of the Southern Christian Leadership Conference.
  • D. Steeles
    Steeles is a residential and commercial neighbourhood located at the northern edge of Scarborough in Toronto, Ontario, known for its diverse community and suburban character.
  • E. Blakely
    Blakely is a given name and surname of English origin that has become popular as a modern unisex first name.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17d5b37cc8190a41d8f304ba8d609 completed April 29, 2026, 3:39 a.m.
Created at: April 17, 2026, 3:31 p.m.