Triple

T12387979
Position Surface form Disambiguated ID Type / Status
Subject Robert Pershing Doerr E295918 entity
Predicate middleName P143 FINISHED
Object Pershing E142899 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: Pershing | Statement: [Robert Pershing Doerr, middleName, Pershing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pershing
Context triple: [Robert Pershing Doerr, middleName, Pershing]
  • A. Pershing chosen
    Pershing is a surname most notably associated with John J. Pershing, the prominent American general who led the American Expeditionary Forces in World War I.
  • B. Pulaski
    Pulaski is a Chicago Transit Authority Blue Line rapid transit station serving the city's West Side.
  • C. Pulaski
    Pulaski is a small city in southern Tennessee that serves as the county seat of Giles County.
  • D. Sherman
    Sherman is the bumbling yet kind-hearted scientist protagonist portrayed by Eddie Murphy in the comedy film "The Nutty Professor."
  • E. Sherman
    Sherman is the curious and good-hearted young boy who travels through time with his genius dog guardian in the animated franchise "Mr. Peabody & Sherman."
  • 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fcf6aa8819080c9a2407a72db2e completed April 10, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62ac939bc819081629b9eef20c4e7 completed May 2, 2026, 4:48 p.m.
Created at: April 8, 2026, 9:54 p.m.