Triple

T5836633
Position Surface form Disambiguated ID Type / Status
Subject William H. Seward E129486 entity
Predicate familyName P18 FINISHED
Object Seward E129486 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: Seward | Statement: [William H. Seward, familyName, Seward]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seward
Context triple: [William H. Seward, familyName, Seward]
  • A. Seward
    Seward is a small coastal city in southern Alaska known as a gateway to Kenai Fjords National Park and a popular hub for fishing, tourism, and marine wildlife viewing.
  • B. Seward chosen
    Seward is an English surname historically associated with several notable figures in literature and politics.
  • C. Daggett
    Daggett is a small unincorporated desert community in San Bernardino County, California, historically known as a railroad and mining town along major transportation routes.
  • D. Wilmot
    Wilmot is the given first name of Hudson Fysh, the Australian aviation pioneer and co-founder of Qantas.
  • E. Harlan
    Harlan is a masculine given name of English origin, historically associated with figures such as U.S. Chief Justice Harlan F. Stone.
  • 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_69c0084af79c81908af128ccc29983d0 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c034a48750819099ae917ae2b54e6d completed March 22, 2026, 6:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a19a6554819086cdae499f4d2247 completed March 23, 2026, 2:12 a.m.
Created at: March 22, 2026, 3:54 p.m.