Triple

T21660839
Position Surface form Disambiguated ID Type / Status
Subject James Harlan E534589 entity
Predicate familyName P18 FINISHED
Object Harlan 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: Harlan | Statement: [James Harlan, familyName, Harlan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harlan
Context triple: [James Harlan, familyName, Harlan]
  • A. Harlan chosen
    Harlan is a masculine given name of English origin, historically associated with figures such as U.S. Chief Justice Harlan F. Stone.
  • B. De Witt
    De Witt is a Dutch surname most famously associated with Johan de Witt, a prominent 17th-century statesman of the Dutch Republic.
  • C. Andrew Harlan
    Andrew Harlan is the time-manipulating Technician protagonist of Isaac Asimov’s science fiction novel "The End of Eternity."
  • D. Hawley
    Hawley is an English-language surname borne by various notable individuals in politics, academia, and other fields.
  • E. Hawley
    Hawley is a small borough in northeastern Pennsylvania known for its historic charm and proximity to the Pocono Mountains and Lake Wallenpaupack.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c07bcb88190a9864672c20325ff completed April 27, 2026, 2 p.m.
Created at: April 16, 2026, 6:36 p.m.